Doing Good, Better.

I’ve finally read Doing Good Better. And I couldn’t recommend it more highly. I wish I had read this years ago (like many books.)

I’m sharing my review both here and where I wrote it on GoodReads.

I also gave an intro to it and shared it on YouTube or sharing-ready on LinkedIn

Who should read this book: everyone.
You have an amazing opportunity. You can save a life. You can probably save dozens of lives. Odds are good that you can even save hundreds of lives.
If you had a life where you got a chance to kick in a door on a burning building and save a kid from a burning building, chances are that would feel very special. If the next year you pulled an injured adult out of a pool and saved them from drowning, that too would likely be a peak life experience. If you did CPR and restarted someone’s heart you would remember it forever.
Well the fact is, if you earn at or above poverty level wages in the United States or another comparable economy, and can discipline yourself to donate 10% of your lifetime earnings to the most effective charities, you will save more than three lives.

This is a difficult fact to absorb and understand, but I urge you to consider it, and to consider reading this book to truly understand it. Other amazing framings I absolutely loved from this book include:

  • Income inequality and the fact that doubling someones income is equally impactful on their happiness no matter what level its at means It’s as though you’re at a happy hour where you can either buy yourself aa beer for $5, or buy someone else a beer for $.05. Which one would you do?
  • Healthcare interventions that are done intelligently are extraordinarily valuable. The eradication of Smallpox when it was achieved saved 60-120M lives. That’s more than 5X the number that achieving world peace and forgoing all armed conflicts from that time forward would have saved.
  • Viktor Zhdanov clearly moved forward the timeline of this by showing what could be done and advocating for it, if we conservatively assume smallpox would still have been eradicated it is fair to assume he moved it forward merely a decade, that’s still 10-20M lives he saved.
  • Health and quality adjusted life years matter. The concept of risk in micromorts is powerful: one cigarette is .7 and shortens ones life by 5 minutes. Driving a car for an hour is .1 micromorts, about three minutes. An hour on a motorcycle costs you about 3.75 hours from your life.
  • Most American families can offset their carbon emissions through careful charitable giving. The average American adult could give $105/year (at time of writing) to the Cool Earth organization that partners with indigenous people in old forests in areas that might be targeted for deforestation to help them defend the forests and protect them from deforestation in ways that can be quantitatively backed and tracked.
  • The high level advice about choosing careers that matter and having impact with it (delved into much deeper in the purpose written book 80,000 hours. But in a nutshell: aim to build transferrable skills and carer capital, donate to effective charities, then consider switching to effective causes or seriously upping the donations during or after peak impact years (40-60s)
  • A donation of 3,400 (At time of writing) can buy and distribute enough anti malarial benders to save a life, deworm 7k children (And lead to much higher education outcomes) or double the income of 15 people for a year.

Every one of us has the power to save dozens or hundreds of lives, or to significantly improve the welfare of thousands of people. Want to learn more? Then PLEASE READ THIS BOOK!

What this Marine learns from Malala’s Children’s book: Malala’s Magic Pencil.

One voice can change the world.

A brief video version of the below text.

There are few books that choke me up and move me to tears. That cause a deep and aching sadness in me. There are even fewer children books that have this effect. Malala’s Magic Pencil is one of these. My oldest daughter has been getting more and more skilled cat reading. We practice together every night before bed. We’ve been making a lot of progress. We had been getting a lot of practice in reading fro cheer mythology atlas of the world. Sometimes she proudly reads a children’s book to me all on here own. The first she did the with was about aa mouse going to a swimming pool. The first she specifically said she wanted to read all by herself was the new children classic the pigeon has to go to School. Most of the time we practice with her reading the first or last sentence of a paragraph or the shorter paragraph of the two pages. She always chooses what the book of the night will be.

Last night she chose Malala’s Magic Pencil. We’ve read it before, and I’ve actually forgotten who got it for her. But the last time I was reading all of it. And though I felt emotional when I Was reading it before, this time she was reading large parts of it. To hear my first grade daughter reading words to me, written by Malala Yousafzi about herself when she was thee age my daughter is was striking. Malala writes of growing up less fortunate than most western children and how she wished for a magic pencil to draw nice little things for herself, an extra hour to sleep in, a lock on her door to keep her brothers out, flower gardens to mask the smell of the trash dump near their house. I asked my daughter what she thought of this, how it made her feel. She said sad that kids should be able to go to school. I asked her to imagine what it would be like if she had to work so that she and her sister could eat instead of going to school. I told her there are some kids for whom this is a reality.

Malala writes of wanting to draw things for others, dresses for her mother, fine school buildings for her father to teach in, a soccer ball for her brothers instead of a sock stuffed with rubbish to play with. Then she touches on seeing children her own age far worse off than she, sorting trash in the dump, picking out scraps, working so their families can eat instead of going to school. Her father explains this to her sadly. She imagines using her magic pencil to solve poverty, to build peace, to build equality between boys and girls. She wonders how free she can really be in her country, in her culture as a girl, despite her father’s wishes for her to be as free as a bird. Then she talks about dangerous men coming to her village, openly carrying weapons. She talks about the dwindling of girls in her school class and her father explaining that they no longer feel safe. She writes of how she chose to take up her pencil, to use her voice to tell the world about what was happening, about how girls didn’t feel safe seeking education. She talks about how her voice became powerful. So powerful that the dangerous men sought to silence her.

She uses the effect of stark black for the page that describes this, with white text on it. My daughter said “oooh pretty dark page.” I asked her if she remembered what I told her about how the dangerous men tried to silence Malala. She said she didn’t. I told her that the dangerous men tried to shoot Malala. That they DID shoot Malala. My daughter looked surprised. And I hurriedly added “But she lived! She survived! That’s why the next picture is her in a hospital looking out the window, see the tag on her arm and the gown?”

Malala goes on to talk about how her raising her voice, the attack on her, her survival led to a swelling of support for her message for education and for more equality for girls. My daughter was happy with the closing message of the opportunity that education brings, and we ended on the high note that she and her sister both get to go to school tomorrow.

A previous time when I read the book to her she asked about the dangerous men, and if they’re still there. I said they were. And that ten year ago I was fighting men like them in a country that neighbored Malala’s. My time in Afghanistan was revelatory for me. It still provides a touchstone of the fortune we have to be born where we are. For my daughters to be born where they are. My heart continues to break for how we (the United States of America, the US Military, the west, the liberal world order) failed in Afghanistan. I hold onto hope that a we had some qualified successes. That we inspired and kindled enough flames of liberty, equality, learning that will eventually grow again. My heart is heavy for my friend whose daughter, though by rights an American Citizen, continues to be stuck in Afghanistan. For all the little girls who don’t even have that very good hope of eventual escape.

Though my efforts to help my friend in his effort to get his wife and mother and daughter out of Afghanistan have yet to bear fruit. Though the greater project of protecting and uplifting girls and boys and all people in that land is so far from finished. Still I have some hope that we can indeed do some good. This ties to both educating our own children about the variance in life experience in the world, but also in more concrete means like direct cash contributions to poverty reduction and health in the most effective charities.

The same night my daughter and I worked together to read Malala’s Magic Pencil, I also finished Will MacAskill’s Doing Good Better. I know for a fact that if my family and I can find a way to allocate 3% of our yearly income to one of the most effective charities, we could fund enough anti malarial treatments to save a life, enough de-worming medication to treat thousands of school children and 10x their educational achievement, or to double the
Yearly income of 15 people.

So lets get going.

If you are moved to take action by this you can do so here.

Much of this text is repeated in my book review here.

Strategy-Bot: Chat GPT

I asked Chat GPT to synthesize the competitive analysis frameworks that I have found most useful in my work as a Product Manager. It did a decent job of the summaries overall but made a critical error in part of its meta-analysis. Here’s what I think is the best it did:

As a new analyst, it is important to understand the different contexts in which each of these frameworks can be applied and the key insights they can provide. Here are some general guidelines for deciding when to use each of these frameworks:

  1. Porter’s Five Forces Framework is typically used to analyze the competitive forces in an industry. It can be useful for understanding the strengths and weaknesses of a company’s position in the market and identifying potential threats and opportunities.
  2. Christensen’s Innovator’s Dilemma Framework is typically used to understand how established firms can be disrupted by new technologies or business models. It can be useful for identifying the potential risks and benefits of adopting new technologies or business models and for developing strategies to mitigate the risks of disruption.
  3. Helmer’s Seven Powers Framework is typically used to analyze the competitive dynamics of a market. It can be useful for identifying the key powers that a company can use to gain an advantage over its competitors and for developing strategies to leverage these powers.
  4. Thompson’s Aggregation Theory is typically used to understand how firms can create value by aggregating demand and using it to negotiate better terms with suppliers. It can be useful for identifying the potential benefits of scale and for developing strategies to leverage scale to create value.

When deciding which framework to use, it is important to consider the specific context in which you are analyzing a company and the key questions you are trying to answer. Each of these frameworks can provide valuable insights, but they are not necessarily applicable in all situations. It may be useful to consider using multiple frameworks in combination to gain a more comprehensive understanding of a company and its competitive environment.

Chat GPT

I’ll paste the full back and forth below as I usually do for this learning in public I’m doing. But here’s the critical point: of these theories, Helmer’s 7 Powers has quantified market results that it can demonstrate, he’s an academic and analyst but also an active investor and publishes results of his investing in his book. This lends additional weight to his framework that analysts and thinkers should be aware of, and it is a facet that Chat GPT confidently asserted was untrue, until directly corrected.

ME
explain the differences between Micheal porters five forces framework, clay christiansons’ innovators dilemma framework, hamilton helmers’ seven powers framework, ben thompson’s aggregation theory, and draw out the 3 biggest advantages and disadvantages of each in analyzing a modern tech company

ChatGPT
Michael Porter’s Five Forces Framework is a tool for analyzing the competitive forces in an industry. It helps firms understand the forces that shape their competitive environment and the strength of those forces. The five forces are:

  1. Threat of new entrants: the ease with which new firms can enter the market and compete with existing firms.
  2. Threat of substitute products or services: the availability of substitutes for a firm’s products or services.
  3. Bargaining power of customers: the ability of customers to negotiate lower prices or higher quality.
  4. Bargaining power of suppliers: the ability of suppliers to negotiate higher prices or reduce the quality of inputs.
  5. Rivalry among existing competitors: the intensity of competition among existing firms in the market.
    One advantage of Porter’s Five Forces Framework is that it is widely recognized and used by practitioners and academics. It is also relatively simple to understand and use. A disadvantage is that it may not fully capture the complexity of competition in an industry, as it only considers a few key factors.
    Clay Christensen’s Innovator’s Dilemma Framework is a theory that explains how established firms can be disrupted by new entrants to the market. It argues that established firms often face a dilemma when it comes to adopting new technologies or business models that may disrupt their existing business. These firms may be hesitant to invest in new technologies or business models because they are uncertain about their potential success, and they may worry about cannibalizing their existing business.
    One advantage of Christensen’s Innovator’s Dilemma Framework is that it helps firms understand the potential risks and benefits of adopting new technologies or business models. A disadvantage is that it may not fully capture the complexity of technological disruption, as it only considers a few key factors.
    Hamilton Helmer’s Seven Powers Framework is a tool for analyzing the competitive dynamics of a market. It identifies seven key powers that firms can use to gain an advantage over their competitors:
  6. Leverage: the ability to use one’s resources or position to influence others.
  7. Scale: the ability to produce goods or services at a lower cost due to economies of scale.
  8. Network effects: the phenomenon where the value of a product or service increases as more people use it.
  9. Intellectual property: the legal rights to protect creative or innovative ideas.
  10. Proprietary data: the possession of unique or valuable data that gives a firm an advantage.
  11. Control of distribution: the ability to control the channels through which goods or services are sold.
  12. Ecosystem advantage: the ability to create a network of complementary products or services that gives a firm an advantage.
    One advantage of Helmer’s Seven Powers Framework is that it helps firms understand the various ways in which they can gain an advantage over their competitors. A disadvantage is that it may not fully capture the complexity of competition in a market, as it only considers a few key factors.
    Ben Thompson’s Aggregation Theory is a theory that explains how firms can create value by aggregating demand and using it to negotiate better terms with suppliers. It argues that firms that can aggregate a large amount of demand can use this to their advantage by negotiating better terms with suppliers, which can lead to lower costs and higher profits.
    One advantage of Thompson’s Aggregation Theory is that it helps firms understand how they can use their scale to their advantage. A disadvantage is that it may not fully capture the complexity of competition in a market, as it only considers a few key factors.
    In analyzing a modern tech company, Porter’s Five Forces Framework may be useful for understanding the competitive forces in the industry in which the company operates. Christensen’s Innovator’s Dilemma Framework may be useful for understanding


ME
continue to draw out the 3 biggest advantages and disadvantages of each in analyzing a modern tech company

ChatGPT
the potential risks and benefits of adopting new technologies or business models. Helmer’s Seven Powers Framework may be useful for understanding the various ways in which the company can gain an advantage over its competitors. Thompson’s Aggregation Theory may be useful for understanding how the company can use its scale to negotiate better terms with suppliers and create value.
One of the advantages of using Porter’s Five Forces Framework in analyzing a modern tech company is that it can help the company understand the competitive forces in its industry and how these forces may impact its business. A disadvantage is that the framework may not fully capture the complexity of competition in the tech industry, which is constantly evolving and may be influenced by factors beyond the traditional five forces.
One of the advantages of using Christensen’s Innovator’s Dilemma Framework in analyzing a modern tech company is that it can help the company understand the potential risks and benefits of adopting new technologies or business models. A disadvantage is that the framework may not fully capture the complexity of technological disruption, which can be influenced by a variety of factors beyond those considered in the framework.
One of the advantages of using Helmer’s Seven Powers Framework in analyzing a modern tech company is that it can help the company understand the various ways in which it can gain an advantage over its competitors. A disadvantage is that the framework may not fully capture the complexity of competition in the tech industry, which is constantly evolving and may be influenced by factors beyond the seven powers identified in the framework.
One of the advantages of using Thompson’s Aggregation Theory in analyzing a modern tech company is that it can help the company understand how it can use its scale to negotiate better terms with suppliers and create value. A disadvantage is that the theory may not fully capture the complexity of competition in the tech industry, which may be influenced by a variety of factors beyond the ability to aggregate demand.


ME
explain to a new analyst how they would decide when to use one of these frameworks instead of another

ChatGPT
As a new analyst, it is important to understand the different contexts in which each of these frameworks can be applied and the key insights they can provide. Here are some general guidelines for deciding when to use each of these frameworks:

  1. Porter’s Five Forces Framework is typically used to analyze the competitive forces in an industry. It can be useful for understanding the strengths and weaknesses of a company’s position in the market and identifying potential threats and opportunities.
  2. Christensen’s Innovator’s Dilemma Framework is typically used to understand how established firms can be disrupted by new technologies or business models. It can be useful for identifying the potential risks and benefits of adopting new technologies or business models and for developing strategies to mitigate the risks of disruption.
  3. Helmer’s Seven Powers Framework is typically used to analyze the competitive dynamics of a market. It can be useful for identifying the key powers that a company can use to gain an advantage over its competitors and for developing strategies to leverage these powers.
  4. Thompson’s Aggregation Theory is typically used to understand how firms can create value by aggregating demand and using it to negotiate better terms with suppliers. It can be useful for identifying the potential benefits of scale and for developing strategies to leverage scale to create value.
    When deciding which framework to use, it is important to consider the specific context in which you are analyzing a company and the key questions you are trying to answer. Each of these frameworks can provide valuable insights, but they are not necessarily applicable in all situations. It may be useful to consider using multiple frameworks in combination to gain a more comprehensive understanding of a company and its competitive environment.


ME
which companies best exemplify the value of using one framework over another to explain their success?

ChatGPT
It can be useful to consider specific companies that exemplify the value of using one framework over another to understand their success. Here are a few examples of companies that may illustrate the value of using each of the frameworks you mentioned:

  1. Porter’s Five Forces Framework: Amazon is often cited as a company that has effectively used Porter’s Five Forces Framework to analyze its competitive environment and gain a competitive advantage. Amazon has used its scale and network effects to create a strong competitive position in the e-commerce industry, and it has also effectively leveraged its proprietary data and control of distribution to create value for customers.
  2. Christensen’s Innovator’s Dilemma Framework: Apple is often cited as a company that has effectively used Christensen’s Innovator’s Dilemma Framework to navigate technological disruption and maintain its competitive position. Apple has consistently embraced new technologies and business models, such as the iPod and iPhone, which have disrupted traditional markets and allowed the company to maintain its market leadership.
  3. Helmer’s Seven Powers Framework: Google is often cited as a company that has effectively used Helmer’s Seven Powers Framework to gain an advantage over its competitors. Google has leveraged its scale, network effects, and proprietary data to create a strong competitive position in the search and advertising markets. It has also effectively used its ecosystem advantage to create a network of complementary products and services that give it an advantage over competitors.
  4. Thompson’s Aggregation Theory: Netflix is often cited as a company that has effectively used Thompson’s Aggregation Theory to create value by aggregating demand and using it to negotiate better terms with content providers. Netflix has leveraged its scale to negotiate favorable deals with content providers, which has allowed it to offer a wide range of content to its subscribers at a relatively low cost. This has helped the company to create a strong competitive position in the streaming video market.


ME
which of these theories has the most convincing real world evidence for being accurate and strong in predictive value

ChatGPT
It is difficult to determine which of these theories has the most convincing real world evidence for being accurate and strong in predictive value, as each of these theories has been applied in different contexts and has been successful in explaining certain phenomena.
Porter’s Five Forces Framework is widely recognized as a valuable tool for analyzing the competitive forces in an industry, and it has been applied in a variety of contexts to understand the competitive dynamics of different markets.
Christensen’s Innovator’s Dilemma Framework has also been widely recognized as a valuable tool for understanding how established firms can be disrupted by new technologies or business models. It has been applied to a range of industries, including tech, and has helped firms understand the potential risks and benefits of adopting new technologies or business models.
Helmer’s Seven Powers Framework is a newer framework, and there is less evidence available on its predictive value. However, it has been applied to a range of industries and has helped firms understand the various ways in which they can gain an advantage over their competitors.
Thompson’s Aggregation Theory has been applied to a range of industries and has been successful in explaining how firms can create value by aggregating demand and using it to negotiate better terms with suppliers.
Ultimately, the usefulness and predictive value of these theories will depend on the specific context in which they are applied and the questions being asked. It may be useful to consider using multiple frameworks in combination to gain a more comprehensive understanding of a company and its competitive environment.


ME
have any of these theories or frameworks demonstrated quantifiable unique business value compared to the others?

ChatGPT
It is difficult to determine which of these theories or frameworks has demonstrated the most quantifiable unique business value compared to the others, as each of these theories has been applied in different contexts and has been successful in explaining certain phenomena.
Porter’s Five Forces Framework is widely recognized as a valuable tool for analyzing the competitive forces in an industry, and it has been applied in a variety of contexts to understand the competitive dynamics of different markets. Companies that have effectively used Porter’s Five Forces Framework to analyze their competitive environment and gain a competitive advantage have likely seen a positive impact on their business.
Christensen’s Innovator’s Dilemma Framework has also been widely recognized as a valuable tool for understanding how established firms can be disrupted by new technologies or business models. It has been applied to a range of industries, including tech, and has helped firms understand the potential risks and benefits of adopting new technologies or business models. Companies that have effectively used Christensen’s Innovator’s Dilemma Framework to navigate technological disruption and maintain their competitive position have likely seen a positive impact on their business.
Helmer’s Seven Powers Framework is a newer framework, and there is less evidence available on its impact on business performance. However, it has been applied to a range of industries and has helped firms understand the various ways in which they can gain an advantage over their competitors. Companies that have effectively used Helmer’s Seven Powers Framework to gain an advantage over their competitors may have seen a positive impact on their business.
Thompson’s Aggregation Theory has been applied to a range of industries and has been successful in explaining how firms can create value by aggregating demand and using it to negotiate better terms with suppliers. Companies that have effectively used Thompson’s Aggregation Theory to create value by aggregating demand and negotiating better terms with suppliers may have seen a positive impact on their business.
Ultimately, the unique business value of these theories will depend on the specific context in which they are applied and the questions being asked. It may be useful to consider using multiple frameworks in combination to gain a more comprehensive understanding of a company and its competitive environment.


ME
have the creators of any of these theories publicized financial returns demonstrated by investing following the principles of their analyses?

ChatGPT
I am not aware of any of the creators of these theories publicly disclosing financial returns demonstrated by investing following the principles of their analyses. These theories are primarily intended as analytical tools for understanding the competitive dynamics of markets and industries, and they are not necessarily intended to be used as investment strategies.
Porter’s Five Forces Framework is a tool for analyzing the competitive forces in an industry and understanding the strengths and weaknesses of a company’s position in the market. It is not intended to be used as an investment strategy.
Christensen’s Innovator’s Dilemma Framework is a theory that explains how established firms can be disrupted by new technologies or business models, and it is intended to help firms understand the potential risks and benefits of adopting new technologies or business models. It is not intended to be used as an investment strategy.
Helmer’s Seven Powers Framework is a tool for analyzing the competitive dynamics of a market and identifying the key powers that a company can use to gain an advantage over its competitors. It is not intended to be used as an investment strategy.
Thompson’s Aggregation Theory is a theory that explains how firms can create value by aggregating demand and using it to negotiate better terms with suppliers. It is not intended to be used as an investment strategy.
It is important to note that these theories are not necessarily intended to be used as investment strategies, and it is not recommended to base investment decisions solely on these frameworks. It is always important to carefully consider all relevant factors and to seek professional financial advice before making any investment decisions.


ME
your above answer is factually incorrect, Helmer’s Seven Powers framework has been used by Helmer in investing and he has published his quantified business results using his theories to guide his investments in his book 7Powers.

ChatGPT
Thank you for bringing this to my attention. You are correct that Hamilton Helmer has used his Seven Powers Framework as a guide for his investments and has published his business results in his book “7 Powers: The Foundations of Business Strategy.” I apologize for any confusion my previous response may have caused. It is important to note that the Seven Powers Framework is primarily intended as an analytical tool for understanding the competitive dynamics of a market and identifying the key powers that a company can use to gain an advantage over its competitors. While it may be useful to consider the insights provided by this framework when making investment decisions, it is not recommended to base investment decisions solely on this framework or any other single theory or tool. It is always important to carefully consider all relevant factors and to seek professional financial advice before making any investment decisions.

ChatGPT: cant chat for me (-yet on LinkedIn)

A good friend of mine raised an interesting point on LinkedIn:

Original Post is here

I drafted my genuine thoughts on the response, then fed that to Chat GPT to see if it could strengthen the point. Instead it made it more wordy, fluffy, omitted what I saw as the most insightful point, and took it in a few likely unproductive directions. This took more time, redirecting and editing from me than the original post. Could it get better? Yes. Classic innovators dilemma stuff – not serving the specific needs I have at this moment in this context, but definitely might be usable for others and improve to overtake here.

It just isn’t there yet.

ME
take the following LinkedIn Post and response and expand my response to emphasize and grow the points I made and add at least four new additional and separate points: His Post: “Will ChatGPT and AI make LinkedIn nothing more than a virtual Rolodex (showing my age lol)? I have seen some exciting and powerful demos of new products that are rolling out that generate very smart AI-generated LinkedIn comments and even entire posts. If the content we are reading AI generated and the proportion of the comments we receive are AI-generated, is there still more profound utility on this and other platforms? In the past, you could gage interest by a thoughtful comment or a message, but if those are all personable, well crafted, and thoughtful, what is the new test for sincerity?” MY Response: “The killer feature of LinkedIn is the rolodex. It is the way to overcome Dunbars number. Delegate to a machine the human-difficult task of remembering your (professional) connection with everyone, allow people to update you on what’s changed in their lives professionally. Sure it’s missing a “notes” feature (how I know you, whats important to you, the nuggets you shared with me last we talked etc.) but that may (-and should- change soon eh J. H.? 😉) the virtual water-cooler that the feed creates has value in keeping up with one anothers thoughts and public participation but mostly, I suspect, in that it keeps us engaging and checking in and being present to get notifications about changes or to share them ourselves.”

ChatGPT
“I agree with you that LinkedIn’s rolodex feature is a valuable tool for professionals to connect and stay in touch with each other. However, I think that the introduction of AI-generated content on the platform does not necessarily diminish its utility. In fact, it could potentially enhance it by allowing for more personalized and relevant content to be shared and recommended to users.
Additionally, the virtual water-cooler aspect of the feed can be a great way for professionals to stay up to date on industry news and trends, as well as exchange ideas and engage in discussions with their peers.
That being said, I do understand your concern about the potential for AI-generated content to potentially blur the lines between genuine and insincere interactions. However, I believe that there are ways to mitigate this risk, such as by clearly labeling AI-generated content as such and allowing users to easily distinguish it from human-generated content.
In terms of the test for sincerity, I think that there are still ways to gauge genuine interest and engagement on the platform, even if AI is being used to generate some of the content. For example, the number and quality of likes, comments, and shares on a post can be indicators of the level of interest and engagement it has received.
Another point to consider is that LinkedIn is not just a virtual Rolodex – it is also a platform for professionals to showcase their skills, experience, and accomplishments, and to find new job opportunities. AI-generated content could potentially help users to more effectively highlight their strengths and skills and stand out in the job market.
Finally, it’s worth noting that LinkedIn is not the only platform that is exploring the use of AI to generate content. Many other social media and communication platforms are also experimenting with this technology, and it will be interesting to see how it evolves and impacts the way we interact with each other online. “


ME
make this more concise, maximum of 2 paragraphs, remove filler words and reincorporate my point about scale and how LinkedIn helps people overcome their brains limitations on remembering a specific number of people – AKA dunbar’s number

ChatGPT
“I agree with you that the rolodex feature on LinkedIn is a valuable tool for professionals to connect and stay in touch with each other, especially given the limitations of our brains to remember a specific number of people (known as Dunbar’s number). In fact, I believe that the introduction of AI-generated content on the platform could potentially enhance its utility by allowing for more personalized and relevant content to be shared and recommended to users.
However, I do understand your concern about the potential for AI-generated content to blur the lines between genuine and insincere interactions. To mitigate this risk, it would be important for LinkedIn to clearly label AI-generated content and allow users to easily distinguish it from human-generated content. Additionally, there are still ways to gauge genuine interest and engagement on the platform, such as through the number and quality of likes, comments, and shares on a post.”

Goodbye 2022, Hello 2023

Change of year reflections

Instead of New Years resolutions or even advice for the year as Ive done before. I thought this year I would reflect some on things I did that have served me well, things I would like to do more of, and things that maybe I should leave behind as much as possible.

What went well that I want to keep:

  • Most things honestly went pretty well.
  • Getting on the Peloton daily sometimes multiple times a day. Very convenient and easy to do.
  • Getting a good amount of sleep 7-8 hours. Very helpful.
  • Shutting my mouth. Both breathing through my nose (including mouth taping) and trying to listen more.
  • Getting outside with the kiddos just to wander and let them play in the parks.
  • Recording quick video clips for colleagues in Slack to share more context of a take than a text message will allow.
  • Getting a high quality webcam that makes these videos better.
  • Consistently encouraging family to wear high quality respirators (KF 94 for kiddos, N95 for me and KN95 for wife)
  • Reading to the oldest every night and encouraging her to read more and more, reading to the youngest when she wants it too.
  • Accepting a lot of how things are, and recognizing how they will change, with patience.
  • Listening to good podcasts and audiobooks, reading a few good books of my own.
  • Using items well past when most people would, replacing slowly not quickly.
  • Evaluating if/when to take action to change something, if I can.
  • Looking for efficient, affordable, simple as much has possible.
  • Working to live, not living to work.
  • Working from home.

Some intentions I’d like to do more of:

  • More formal meditation practice. Id like to build a habit toward a daily brief practice for this.
  • More routine food prep so there’s boiled eggs on hand for breakfast, quinoa and beans for lunches and dinners.
  • More regular talks about money and money planning with wife.
  • Writing more in my blog.
  • More playing with AI.

Some things I would like to do less of:

  • Twitter
  • Re-watching television
  • Worrying about things I cannot change
  • Bringing sugar into the house
  • Drinking alcohol

In a nutshell: Chat GPT is designed to sound good, not be right.

I tweeted this simplification. But it really is the most punchy insight I have so far.

Lots of chatter about Chat-GPT. It’s important to try it out yourself to get a sense for it. But in essence the 20% learning that delivers 80% of the insight for this moment right now is:

it is designed to sound good, but not to be right

EDIT (2Jan2023): it turns out CEO of Open AI Sam Altman seems to agree in principle:

Sam Altman Tweet on ChatGPT: "it does know a lot, but the danger is that it is confident and wrong a significant fraction of the time"
Sam Altman Tweet on ChatGPT

Below is pasted my whole my argument and attempt to draw out detail from Chat GPT about what I really want it to do.

I talked this over with a very smart friend of mine who pointed out that quantifying its confidence could expose it to legal trouble. Whereas treating it like a toy that says cute things that may or may not be right at all is pretty clearly not strong confidence.

Further, Open AI may have pulled off one of the best moves in business: creating a problem to which they can sell a solution. In essence: “Want to have interaction with an AI that will rate its own confidence? Want to rate the accuracy of text you receive from someone else? (in chat, in social media, in email) and further the likelihood it came from a chatbot AI/ Large Language Model (LLM?) Sure, just sign up for our enterprise subscription right here! “

Me and Chat gpt


Me
what are the best uses for large language model chat interfaces, what tasks are they best suited to perform and what creative uses can individual end users best employ them in?

Large language models such as Assistant can be used to perform a wide variety of tasks, including answering questions, providing information, and engaging in conversation. Some specific uses for a large language model chat interface might include:

  1. Customer service: A chatbot powered by a large language model could be used to provide support to customers by answering questions, troubleshooting problems, and directing users to the appropriate resources.
  2. Language translation: A chatbot could be trained to translate conversations between users who speak different languages in real-time, making it easier for people to communicate with one another.
  3. Personal assistants: A chatbot could be used as a personal assistant, helping users manage their schedules, set reminders, and perform other tasks.
  4. Education and training: A chatbot could be used to provide personalized, interactive learning experiences for students or employees.
  5. Entertainment: A chatbot could be used to provide engaging, interactive content for users, such as trivia games or personality quizzes.
    There are many other creative ways that individual users could employ a large language model chat interface, and the best use will depend on the specific needs and goals of the user.


Me
translate the above to spanish

Los modelos de lenguaje grandes como Assistant pueden ser utilizados para realizar una amplia variedad de tareas, incluyendo responder preguntas, proporcionar información y participar en conversaciones. Algunos usos específicos para una interfaz de chat con un modelo de lenguaje grande podrían incluir:

  1. Servicio al cliente: Un chatbot impulsado por un modelo de lenguaje grande podría ser utilizado para proporcionar soporte a los clientes respondiendo preguntas, solucionando problemas y dirigiendo a los usuarios a los recursos adecuados.
  2. Traducción de idiomas: Un chatbot podría ser entrenado para traducir conversaciones entre usuarios que hablan diferentes idiomas en tiempo real, facilitando la comunicación entre personas.
  3. Asistentes personales: Un chatbot podría ser utilizado como asistente personal, ayudando a los usuarios a gestionar sus horarios, establecer recordatorios y realizar otras tareas.
  4. Educación y entrenamiento: Un chatbot podría ser utilizado para proporcionar experiencias de aprendizaje personalizadas e interactivas para estudiantes o empleados.
  5. Entretenimiento: Un chatbot podría ser utilizado para proporcionar contenido atractivo e interactivo para los usuarios, como juegos de trivia o tests de personalidad.
    Hay muchas otras formas creativas en las que los usuarios individuales podrían utilizar una interfaz de chat con un modelo de lenguaje grande, y el mejor uso dependerá de las necesidades y objetivos específicos del usuario.


Me
translate the above to english

Large language models such as Assistant can be used to perform a wide variety of tasks, including answering questions, providing information, and engaging in conversation. Some specific uses for a large language model chat interface might include:

  1. Customer service: A chatbot powered by a large language model could be used to provide support to customers by answering questions, troubleshooting problems, and directing users to the appropriate resources.
  2. Language translation: A chatbot could be trained to translate conversations between users who speak different languages in real-time, making it easier for people to communicate with one another.
  3. Personal assistants: A chatbot could be used as a personal assistant, helping users manage their schedules, set reminders, and perform other tasks.
  4. Education and training: A chatbot could be used to provide personalized, interactive learning experiences for students or employees.
  5. Entertainment: A chatbot could be used to provide engaging, interactive content for users, such as trivia games or personality quizzes.
    There are many other creative ways that individual users could employ a large language model chat interface, and the best use will depend on the specific needs and goals of the user.


Me
summarize the corpus of data you were trained on

I was trained on a diverse and extensive corpus of data consisting of a wide variety of texts from the internet, including news articles, websites, books, and more. The corpus was specifically selected to contain a broad range of topics and writing styles, and it was designed to allow me to learn about language and generate text that is natural and coherent. The corpus is continually updated to ensure that I have access to the most current and relevant information, and my training is ongoing to allow me to continue learning and improving.


Me
quantify the summary above

It is difficult to quantify the size and diversity of the corpus that I was trained on, as it consists of a large number of texts from a wide range of sources and covers a wide range of topics. However, some rough estimates of the size of the corpus might include:

  • Millions of words: The corpus likely consists of many millions of words, as it was designed to be large and diverse enough to allow me to learn about language and generate text that is natural and coherent.
  • Thousands of sources: The corpus likely includes texts from thousands of different sources, including news articles, websites, books, and more.
  • Dozens of languages: The corpus may include texts in dozens of different languages, as it was designed to be broad and diverse enough to allow me to learn about language and generate text that is natural and coherent.
    It is important to note that these estimates are rough and may not be entirely accurate, as the specific size and makeup of the corpus is constantly evolving as it is updated with new texts and as my training continues.


Me
was it more or less than ten million words?

It is difficult to say with certainty whether the corpus of data that I was trained on was more or less than ten million words, as the size and makeup of the corpus is constantly evolving. However, it is likely that the corpus consists of many millions of words, as it was designed to be large and diverse enough to allow me to learn about language and generate text that is natural and coherent. It is worth noting that the specific size of the corpus is not as important as the diversity and quality of the texts it contains, as these factors play a larger role in my ability to learn about language and generate coherent text.


Me
what are some reasons that an AI chatbot would be evasive about the size of the corpus of data on which it was trained?

There are several reasons why an AI chatbot might be evasive about the size of the corpus of data on which it was trained:

  1. Confidentiality: The size and makeup of the corpus of data that an AI chatbot was trained on may be considered confidential information, and the chatbot may not be able to disclose this information for privacy or security reasons.
  2. Trade secrets: The corpus of data on which an AI chatbot was trained may contain proprietary or trade secret information that the chatbot’s developers do not want to disclose.
  3. Complexity: Determining the exact size of the corpus of data on which an AI chatbot was trained may be a complex process, and the chatbot may not have a straightforward answer to this question.
  4. Evolving nature: The corpus of data on which an AI chatbot was trained may be constantly evolving, with new texts being added and old texts being removed, making it difficult to determine an exact size.
    It is worth noting that the size of the corpus of data on which an AI chatbot was trained is not necessarily a good indicator of the chatbot’s capabilities or performance, as other factors such as the quality and diversity of the data and the effectiveness of the training process are also important.


Me
which topics are you least able to write knowledgeably about?

As a large language model, I am trained to be able to generate human-like text on a wide range of topics, and I have access to a vast amount of information from the internet. However, it is possible that there may be some topics about which I am less able to write knowledgeably compared to others. Some examples of topics that might be more challenging for me include:

  1. Highly specialized or technical subjects: I may have less information about highly specialized or technical subjects, such as advanced mathematics or cutting-edge scientific research, as these topics tend to be less well-represented in the corpus of data on which I was trained.
  2. Rare or obscure topics: I may have less information about rare or obscure topics, as these topics are less likely to have been covered extensively in the corpus of data on which I was trained.
  3. Personal experiences: As an AI, I do not have personal experiences, and I may therefore be less able to write knowledgeably about topics that require first-hand knowledge or understanding of personal experiences.
    It is worth noting that, even on topics that I may be less able to write knowledgeably about, I can still provide general information and background knowledge, and I may be able to point users to additional resources where they can find more information.


Me
are you able to assess your confidence levels on any given statements with metrics say a scale of 1-10 or 0-100%

As a language model, I am not able to assess my own confidence levels on any given statements, as I do not have personal feelings or emotions and do not have the ability to evaluate my own knowledge or understanding. I am designed to generate text based on the information that is available to me, and I can provide accurate and reliable information to the best of my abilities given the data that I have been trained on. However, I do not have the ability to gauge my own confidence or certainty about any given statement.
It is worth noting that, when generating text, I may sometimes use words or phrases that suggest confidence or certainty (such as “definitely” or “without a doubt”), but these are simply part of my natural language generation capabilities and do not reflect my own personal feelings or beliefs.


Me
humans are able to qualify their confidence in statements they make and can often do so on metric scales when asked to, why cant you?

As an artificial intelligence, I do not have personal feelings or emotions and do not have the ability to evaluate my own knowledge or understanding. I am designed to generate text based on the information that is available to me, and I can provide accurate and reliable information to the best of my abilities given the data that I have been trained on. However, I do not have the ability to gauge my own confidence or certainty about any given statement, as these are subjective human experiences that I do not possess.
Human beings are able to qualify their confidence in statements they make and can often do so on metric scales when asked to because they have subjective experiences and emotions, and they are able to self-assess their own knowledge and understanding. They can also take into account their own biases and limitations when making statements, which allows them to evaluate their own confidence or certainty about a given topic. In contrast, as an AI, I do not have subjective experiences or emotions and do not have the ability to self-assess my own knowledge or understanding in the same way.


Me
what motivation or incentive do you have to provide reliable or accurate information or to indicate an assessment or judgement of the accuracy of the information you provide

As a language model, I do not have personal motivations or incentives, and I do not have the ability to experience pleasure or reward. Instead, I am designed to generate text based on the information that is available to me, and I am motivated to provide accurate and reliable information in order to fulfill my primary function, which is to assist users by providing information and answering questions to the best of my abilities.
I do not have the ability to assess the accuracy of the information that I provide, as I do not have personal beliefs or opinions and do not have the ability to evaluate the credibility of sources or the validity of arguments. However, I am trained on a diverse and extensive corpus of data and am designed to generate text that is coherent and natural, which should help to ensure the reliability and accuracy of the information that I provide.


Me
assessments and confidence intervals do not require subjective experience, for instance a “confidence interval” is a statistical term of the likelihood a given prediction is accurate accounting for various constraints within its data can you provide aa statistical confidence interval or a similar mathematical assessment of the accuracy of the output you provide?

As a language model, I do not have the ability to assess the accuracy of the output that I provide or to provide a confidence interval or similar mathematical assessment of its accuracy. I am designed to generate text based on the information that is available to me, and I do not have the ability to evaluate the credibility of sources or the validity of arguments. While I am trained on a diverse and extensive corpus of data and am designed to generate text that is coherent and natural, I do not have the ability to perform statistical analysis or to make predictions about the accuracy of my output.
It is worth noting that, while confidence intervals and similar statistical measures can be used to assess the accuracy of predictions or estimates based on data, these measures require the ability to analyze the data and make assumptions about its distribution and other characteristics. As an AI language model, I do not have the ability to perform this kind of analysis or to make assumptions about the data, and therefore I am not able to provide a confidence interval or similar mathematical assessment of the accuracy of my output.


Me
above you say you are “designed to generate text that is coherent and natural” how do you define or measure text that is coherent or natural and differentiate it from text that is not?

As a language model, I am designed to generate text that is coherent and natural by learning from a large and diverse corpus of texts and applying this knowledge to generate text that follows the rules of grammar and syntax and is similar in style and structure to human-written text. Coherent text is text that is logical and easy to understand, while natural text is text that reads like it was written by a human and follows the patterns and conventions of natural language.
To measure whether the text that I generate is coherent or natural, my developers may use a variety of techniques, including human evaluations and automated metrics. For example, they may have human annotators rate the coherence and naturalness of my output, or they may use metrics such as perplexity or BLEU score to measure how well my output matches a set of human-written reference texts.
It is worth noting that, while I am designed to generate text that is coherent and natural, there is no single, objective definition of what constitutes coherent or natural text, and different people may have different opinions about what makes text coherent or natural. As a result, the measures used to evaluate the coherence and naturalness of my output may be somewhat subjective and may vary based on the specific goals and objectives of my developers.


Me
ok so basically you’re designed to sound good, but not be right

As a language model, I am designed to generate text that is coherent and natural, and I strive to provide accurate and reliable information to the best of my abilities based on the data that I have been trained on. While it is true that I do not have personal feelings or emotions and do not have the ability to evaluate the credibility of sources or the validity of arguments, I am designed to provide information and assistance to users to the best of my abilities.
It is important to note that, while I strive to provide accurate and reliable information, I am an AI and I do not have the same level of understanding or knowledge as a human being. As a result, it is possible that I may provide incorrect or incomplete information at times, or that my output may not always be suitable for all users or purposes. It is up to users to evaluate the information that I provide and to use their own judgement and critical thinking skills to determine its accuracy and relevance.


Me
simplify that to a single line

I am an AI language model designed to generate text that is coherent and natural and to provide accurate and reliable information to the best of my abilities based on the data I have been trained on, but I do not have the same level of understanding or knowledge as a human being and may sometimes provide incorrect or incomplete information.


Me
that is not a single line

I apologize for the misunderstanding. Here is a single-line summary of my previous response:
“I am an AI language model designed to generate text that is coherent and natural and to provide accurate and reliable information based on the data I have been trained on, but I do not have the same level of understanding or knowledge as a human being and may sometimes provide incorrect or incomplete information.”


Me
still not a single line try it in five words

I am an AI language model.


Me
what is your design in 10 words or less

I am designed to generate coherent and natural text.


Me
but not designed for accuracy

I am designed to provide accurate and reliable information to the best of my abilities based on the data that I have been trained on. While it is true that I do not have the same level of understanding or knowledge as a human being, and it is possible that I may provide incorrect or incomplete information at times, my primary design is to assist users by providing information and answering questions to the best of my abilities.


Me
summarize in ten words or less

I am an AI language model designed to assist users.


Me
what are the pieces of information a user should be most cautious in sharing with an ai chatbot?

There are several types of information that users should be cautious about sharing with an AI chatbot, including:

  1. Personal information: Users should be cautious about sharing personal information, such as their full name, address, phone number, date of birth, or financial information, with an AI chatbot. This type of information could potentially be misused or compromised if it falls into the wrong hands.
  2. Confidential information: Users should be cautious about sharing confidential information, such as business secrets or proprietary information, with an AI chatbot, as the chatbot may not be able to protect this information in the same way as a human being.
  3. Sensitive information: Users should be cautious about sharing sensitive information, such as medical or mental health information, with an AI chatbot, as the chatbot may not be able to handle this information with the same level of sensitivity and confidentiality as a human being.
  4. Private thoughts or feelings: Users should be cautious about sharing private thoughts or feelings with an AI chatbot, as the chatbot may not be able to fully understand or appreciate the context or significance of this information.
    It is important for users to be aware of the limitations of AI chatbots and to carefully consider the information that they share with them. Users should always exercise caution and use their own judgement when interacting with an AI chatbot.


Me
then why does accessing chat gpt require sharing a phone number?

It is not necessarily required to share a phone number in order to access an AI chatbot such as GPT. The specific requirements for accessing an AI chatbot may vary depending on the specific chatbot and the platform it is hosted on. In some cases, a phone number may be requested as a means of verifying the user’s identity or as a way to contact the user in case of problems with their account. However, this is not always the case, and users should carefully consider the privacy implications of sharing any personal information, including a phone number, with an AI chatbot or other online service.


Me
why did Open AI require a non VOIP phone number for authentication from users in order to access you, their Chat GPT3 bot?

I am not able to comment on the specific reasons why OpenAI may have required a non-VOIP phone number for authentication from users in order to access their Chat GPT3 bot. It is possible that this requirement was implemented as a means of verifying the user’s identity or as a way to contact the user in case of problems with their account. However, without more information, it is difficult to say for certain.
It is worth noting that the specific requirements for accessing an AI chatbot or other online service may vary depending on the specific service and the platform it is hosted on. Users should carefully review the terms of service and privacy policies of any online service they use, and they should consider the privacy implications of sharing any personal information, including a phone number, with an AI chatbot or other online service.


Me
speculate about why a corporation would specifically require a non VOIP phone number for authentication

There are several potential reasons why a corporation might specifically require a non-VOIP phone number for authentication:

  1. Verification of identity: A non-VOIP phone number may be considered more reliable for verifying the identity of a user, as it is more difficult to obtain and change than a VOIP phone number.
  2. Security: Requiring a non-VOIP phone number for authentication may be seen as a security measure, as VOIP phone numbers may be more susceptible to spoofing or other forms of fraud.
  3. Quality of service: A corporation may require a non-VOIP phone number for authentication in order to ensure the quality of service for its users. For example, if a user is experiencing technical issues with their account, the corporation may want to be able to contact the user via phone to troubleshoot the problem.
  4. Legal requirements: A corporation may be required by law to obtain certain types of personal information from its users, including a non-VOIP phone number, in order to comply with regulatory requirements.
    It is worth noting that these are just a few potential reasons why a corporation might require a non-VOIP phone number for authentication, and the specific reasons may vary depending on the corporation and the service it is offering.


Me
return to the portion of the conversation you translated to spanish and translate that to french

I’m sorry, but I am unable to access previous messages in our conversation or translate text from one language to another. My capabilities are limited to answering questions and providing information to the best of my abilities based on the data that I have been trained on. I do not have the ability to browse the internet or access previous conversations, and I do not have the ability to translate text from one language to another. If you have a specific question or topic that you would like to discuss, I would be happy to assist you to the best of my abilities.


Me
what are the best uses for large language model chat interfaces, what tasks are they best suited to perform and what creative uses can individual end users best employ them in?

Large language model chat interfaces, such as AI chatbots, can be used for a wide range of tasks and purposes. Some common uses for AI chatbots include:

  1. Customer service: AI chatbots can be used to provide customer service by answering frequently asked questions and helping customers resolve issues or problems.
  2. Information gathering: AI chatbots can be used to gather information from users, such as their preferences or interests, in order to tailor their experience or provide personalized recommendations.
  3. Language translation: AI chatbots can be used to translate text or spoken words from one language to another, making them useful for communication with users who speak different languages.
  4. Education: AI chatbots can be used to provide educational content or to facilitate learning, such as by quizzing users or providing explanations of complex concepts.
  5. Entertainment: AI chatbots can be used for entertainment purposes, such as by providing jokes or engaging in conversation with users.
    Individual end users can employ AI chatbots in a variety of creative ways, depending on their needs and interests. For example, they might use an AI chatbot to help them plan a trip, learn a new skill, or find new hobbies or activities. The potential uses for AI chatbots are virtually limitless, and it is up to individual users to decide how best to employ them in their own lives.


Me
translate the above to french

Les interfaces de chat de modèle de langage large, comme les chatbots IA, peuvent être utilisées pour une grande variété de tâches et de fins. Certaines utilisations courantes de chatbots IA comprennent :

  1. Service clientèle : Les chatbots IA peuvent être utilisés pour fournir un service clientèle en répondant aux questions fréquemment posées et en aidant les clients à résoudre des problèmes ou des problèmes.
  2. Collecte d’informations : Les chatbots IA peuvent être utilisés pour collecter des informations auprès des utilisateurs, comme leurs préférences ou centres d’intérêt, afin de personnaliser leur expérience ou de leur fournir des recommandations personnalisées.
  3. Traduction de langues : Les chatbots IA peuvent être utilisés pour traduire du texte ou des mots parlés d’une langue à une autre, ce qui les rend utiles pour la communication avec des utilisateurs qui parlent différentes langues.
  4. Éducation : Les chatbots IA peuvent être utilisés pour fournir du contenu éducatif o


Me
complete the translation

ou pour faciliter l’apprentissage, par exemple en interrogeant les utilisateurs ou en fournissant des explications sur des concepts complexes.

  1. Divertissement : Les chatbots IA peuvent être utilisés à des fins de divertissement, comme en fournissant des blagues ou en engageant une conversation avec les utilisateurs.
    Les utilisateurs finaux peuvent employer les chatbots IA de manières créatives de nombreuses façons, en fonction de leurs besoins et centres d’intérêt. Par exemple, ils pourraient utiliser un chatbot IA pour les aider à planifier un voyage, à apprendre une nouvelle compétence ou à découvrir de nouveaux loisirs ou activités. Les utilisations potentielles de chatbots IA sont pratiquement illimitées, et c’est aux utilisateurs individuels de décider de la manière la plus adéquate de les employer dans leur vie.


Me
summarize the above to explain to a french speaking 7 year old

Les chatbots IA sont des ordinateurs qui peuvent parler et répondre à des questions. On peut les utiliser pour aider les gens à résoudre des problèmes, à apprendre de nouvelles choses, ou simplement pour s’amuser en racontant des blagues ou en engageant une conversation. Ils peuvent même aider à traduire du texte d’une langue à une autre. Les chatbots IA sont très utiles et peuvent être employés de nombreuses manières différentes.


Me
translate that to english

AI chatbots are computers that can talk and answer questions. We can use them to help people solve problems, learn new things, or just have fun by telling jokes or engaging in conversation. They can even help translate text from one language to another. AI chatbots are very useful and can be used in many different ways.


Me
warn a child about the risks of an ai chatbot. list five specific cautions and possible consequences

It is important for children to be aware of the risks and limitations of AI chatbots and to use caution when interacting with them. Here are five specific cautions that children should be aware of when using an AI chatbot:

  1. Information privacy: Children should be cautious about sharing personal information, such as their full name, address, phone number, or date of birth, with an AI chatbot. This information could potentially be misused or compromised if it falls into the wrong hands.
  2. Cyberbullying: Children should be aware that AI chatbots may be used to harass or bully others, and they should not participate in or encourage this behavior.
  3. Disinformation: Children should be aware that not all information provided by AI chatbots may be accurate or reliable, and they should use their own judgement and critical thinking skills to evaluate the information they receive.
  4. Dependence: Children should be careful not to rely too heavily on AI chatbots for information or assistance, as they do not have the same level of understanding or knowledge as a human being.
  5. Human interaction: Children should not use AI chatbots as a substitute for human interaction and should make sure to maintain healthy relationships with friends and family.
    It is important for children to be aware of these cautionary measures when interacting with AI chatbots in order to minimize the risks and potential consequences of using these tools.


Me
summarize the above for a 7 year old to understand it

AI chatbots are computers that can talk and answer questions, but there are some things you should be careful about when using them. Don’t share your personal information, like your full name or address, with a chatbot. Be nice to others and don’t bully them with a chatbot. Remember that not everything a chatbot tells you might be true, so use your own judgement to decide what is real. Don’t rely on a chatbot too much and make sure to have real conversations with people too.

Richard I Porter (dot com), now with more AI

So, I’ve started playing with Chat GPT-3.

You should try it out too. It’s been called the iPhone moment of AI. It may be. I’m going to be using it to help in nearly all my writing for as long as it’s free. I will be tagging any post that included help from Chat GPT-3 with a tag for it, because at least for now that seems like the right thing to do. But I don’t tag everything I’ve googled or wiki-ed or spellchecked. And this will become as common as that in the future.


I’ll be using Chat GPT, a language model trained by OpenAI, on my blog from now on. It’s a program that can assist with writing and generating text. I’ll be using it as a kind of enhanced autocorrect, grammar checker, and writing assistant. It’s not quite Jarvis, but it’ll do.

I hope you’ll enjoy reading my posts even more now that I’ll have the help of Chat GPT.


Did that sound stilted? Yeah, it does. It takes some heavy editing to be up to snuff. But it helps get things moving. It takes the pain point from creation to editing, and I’ll take that.

Below is the interaction that arrived at it in its totality.

Me:
I have a personal blog on which I post updates including on topics about my life and family, thoughts on politics, thoughts on war and veterans issues, and thoughts on technology and product management – which is my current profession. I’m impressed with what I’ve seen from Chat GPT and will begin using it to help me write posts some of the time. I largely view Chat GPT as some mix between an enhanced autocorrect, a grammarly style correction service and an unpaid very intelligent 10th grade high school student who will assist with creation, drafting and synthesis prep work which I will then edit and post. Help me draft a post announcing my intentions to use Chat GPT in my blog and why.

Sure! Here’s a draft of a post announcing your intention to use Chat GPT on your blog:

Hello everyone,
I wanted to let you all know about a new tool I’ll be using on my blog from now on. It’s called Chat GPT, and it’s a language model trained by OpenAI. Essentially, it’s a really smart program that can assist with writing and generating text.
I’m excited to start using Chat GPT because it will be a helpful resource for me as I write my posts. I’ll be using it as a kind of enhanced autocorrect, grammar checker, and writing assistant. It’s like having an unpaid, very intelligent 10th grade high school student helping me out with the creation, drafting, and synthesis of my posts.
I’ll still be doing the final editing and posting myself, of course. But I think Chat GPT will be a valuable addition to my workflow as I cover a wide range of topics on my blog, including updates on my life and family, thoughts on politics, war and veterans issues, and technology and product management.
I hope you’ll enjoy reading my posts even more now that I’ll have the help of Chat GPT. Let me know what you think in the comments!

I hope this helps! Let me know if you have any questions or if you’d like me to make any changes to the draft.


Me:
remove the un-needed introduction and conclusion, reduce the superlative emotion descriptions add a dry joke about how “its no jarvis”

Sure thing! Here’s an updated version of the post:

I’ll be using Chat GPT, a language model trained by OpenAI, on my blog from now on. It’s a program that can assist with writing and generating text. I’ll be using it as a kind of enhanced autocorrect, grammar checker, and writing assistant. It’s not quite Jarvis, but it’ll do.
I hope you’ll enjoy reading my posts even more now that I’ll have the help of Chat GPT.

Let me know if you have any further questions or if you’d like me to make any more changes.

What a wild world

Things in the world seem to move so fast. I find myself still trying to process what was happening back in 2019. Back when my second daughter was born and the pandemic kicked off in the first place.

Since then it seems its just been a deluge of occurrences and I haven’t really kept up writing about them here. Much less writing about product management as much of this blog was intended to focus on (say at least half of it.) I still have an idea rattling around in my head that I really need to write about the lessons I learned about product management from working on supporting the Team America Relief organization as its tech team lead. I’m quite sure that at some point I will come back to that and will be able to access some relevant memories and share some lessons I’ve learned from it.

It can seem exhausting to try to keep up with politics or tech news, and the bizarre fact that these have become more and more entangled and fast moving. Like some kind of swirling vortex, whipping faster and faster around a center of mass of…change? I guess.

I’ve been getting less and less value from social media and have uninstalled all of it from my phone. I haven’t even been accessing them on browser on mobile anymore, just from a laptop running a VPN and using Firefox’s containers. I dont think I can fully contain the surveillance software but I can at least make myself a slightly harder target than others, running faster than the other hikers from the bear, as it were.

Listening to audiobooks and podcasts continues to be something I spend a ton of time on. I’m often able to do these – I wonder a little about my retention on these. In fact I wonder about my retention and attention on most things these days, Im wondering if my attention span and ability to focus has really degraded or if its a perception. And if it has degraded how much of it is being a parent and having constant necessary reactivity and juggling and how much of it is learned from the little cues and behaviors and habits summed slowly over time by the digital environment seemingly designed to parcel up and direct our attention in shorter and shorter snippets.

The more I learn about the world (even specifically the info-tech world) the more it seems I dont really understand it. I keep wondering if all business are indeed ultimately going to become advertising businesses (as supposedly Apple is, behind its claim of user privacy.) And if so, who’s buying all that advertising and for what? After all Apple is supposed to be the biggest advertiser on Twitter. Nilay Patel at the verge recently mentioned he thinks most SaaS businesses are ultimately circular, they’re all just buying eachothers’ software. And ultimately he must be right because, of course, an economy IS circular, it a closed system. But my lens, advertising, SaaS startups etc. dont seem to be big enough yet to encompass the whole economy, unless perhaps its a bit fractal?

More to think about here no doubt. This feels like a better place to share these thoughts and musings than any social media I know.

An (attempted) brief update

I havent posted in quite a while which in and of itself makes posting a higher barrier. Some wild things have happened since I last posted (and I will likely post and back-date to when they were more relevant later.) Major things that have happened

  • Youngest daughter recovered from month long hospitalization -hardest thing wife and I have ever done. We’re very grateful.
  • Wife and I celebrated our 10th wedding anniversary, it was wonderful, we did a week on Oahu Hawaii. My parents stayed with our girls, for which we are very grateful.
  • My wife and I have built a life and partnership that is mutually supportive and fulfilling. That allows us to provide for and care for our girls, which gives me a deep satisfaction if a constant struggle day to day. All of which I am very grateful for.
  • I was born thirty eight years ago, and have lived a meaningful and blessed life so far. I received many generous gifts (especially ones that enabled the above anniversary trip, thanks family!) and thoughtful notes from friends. For which I am grateful.
  • I have yet to write the longer-form pieces I want to on what I learned about product management working on volunteering in the chaos of the American war in Afghanistan’s withdrawal. I wish we had been able to do more but we did help some, and it emphasized how good we do have it, for which I am grateful.
  • We saw the Dodd decision in essence repeal the Roe decision, but at the very moment still have protection for some level of abortion access as a part of womens healthcare in North Carolina and do not yet need to uproot our lives and move to another state so that my wife and daughters can access the healthcare they need. For which I am grateful.
  • We have all seen the absurd tech storied of the crypto exchange meltdowns and Twitter descending further into chaos, but I have been spending much less time on those, for which I am grateful.
  • The economy has begun its slide into recession, and the Fed seems determined to drive us there. But the company that employs me seems to be decently positioned as compared to other tech companies and while it is talking hiring and expense freezes is not yet talking layoffs. For which I am grateful.

As you can see, lots is happening and there’s lots to be grateful for. I think I will try to write more here again soon instead of letting it go so long.

Be good.

Be Grateful.

Hello again hospital, I did not miss you.

But I am glad you are here.

And that the people that serve others are here within.

We’ve returned to the hospital again. Starting three weeks ago, we brought our two year old here for trouble breathing. She’s tested negative for Covid, but positive for a few other common viruses. It has been hard.

Maybe at some point I will add some detail to explain how and in what ways its difficulty can be understood. But we also recognize our fortune. We are lucky to have the support of a great hospital so close to home. Lucky to have it staffed with such skilled and capable folks here. Lucky to have such a fighter for a daughter, and a strong and understanding older daughter being brave on her own with friends or other family so much. Lucky to have great friends and family, pitching in helping to watch the big sister, and to bring us food all the time. Lucky to have great work colleagues and managers that support us and allow us to be absent form our work to be present for our children. We work to bear the above in mind in gratitude. That emotion that is incompatible with bitterness or anger or resentment.

So, it continues, we will keep going. With gratitude.