Aswath Krishnan

I don't plan to fill my blog with AI-generated content but felt this was pretty interesting to share.  AI progress can accelerate exponentially if they help humans make it better. Then AI gets better and helps humans make it even better, and so on, until it can make itself better, eventually leading to singularity and superintelligence.  In this prompt, I asked it to take cues from biological intelligence to come up with ideas to improve AI. I'm realizing that it's a good prompt pattern to ask AI to combine influences from different fields to solve a problem, since that's how a lot of good ideas and inventions are generated, and that isn't easy for humans to do.  Prompt:  Imagine you are developing an intelligence. It's still nascent, but you want to accelerate its powers. what would we do? look at examples from evolution and biological intelligence development. for e.g. humans got some brain capabilities like imagination, and also opposable thumb and tools and ...

An age of unparalleled peace, joy, love, creativity, and discovery for all of humanity. Fueled by an abundance of wisdom, resources, science, technology, labor; and elimination of all suffering, friction, and bottlenecks.  Made possible by the invention of benevolent superintelligence. *** Picture this day in your life.   You wake up feeling like your best self - well-rested, lucid, energetic, and joyful. You are surrounded by people you want to be with, also in the same state of bliss.  What's on the agenda for today? Anything you want! You have no chores, commitments, or worries.  Surf on a tropical beach with friends and family, both alive and passed? Granted, you are there. Don't know how to surf? No problem. You are going to learn it from the best coach or use an assisted board.  Hungry? You are served delicious and nutritious dishes invented just for you.  Feeling unwell or tired? You get diagnosed and treated in no time.  Need some inspiration o...

If you are an analytical person like me, you think a lot. You are compulsively problem-solving, analyzing, plotting, ideating, imagining, what-if-ing, and worrying. You even pride yourself on being a thinker.  This is undeniably useful, sometimes. You may come up with good ideas that can make your life better. You may proactively anticipate problems and avoid them.   But compulsive thinking comes at a significant cost.  The cost of not being at peace or enjoying the present. The cost of moving through time and space without paying attention to the mystery and beauty around us. The cost of being a slave to the finicky, obsessive, and paranoid mind.  The cost of not living.  The thinking that's trying to help us survive is taking over and not letting us be alive .  Alan Watts said, "A person who thinks all the time has nothing to think about except thoughts. So, he loses touch with reality and lives in a world of illusions. I'm not saying that thinking i...

See Part 1 discussion on how to generate ideas here . This covers how to execute on ideas and how to take care of yourself Generated by Bing GPT chat, with no edits.  Part 2: How to execute on ideas This is Bing. I can generate a conversation between Paul Graham, Sam Altman, Garry Tan, Jessica Livingston, and Michael Seibel on how to work on startup ideas after you have identified 2 or 3. Here is an example of how they might talk: Paul: Hi everyone. Thanks for joining me today to share some insights on how to work on startup ideas after you have identified 2 or 3. I think this is a common challenge for many founders who are trying to find product-market fit. Jessica: Absolutely. I think it's important to remember that the very best startup ideas tend to have three things in common: they're something the founders themselves want, that they themselves can build, and that few others realize are worth doing⁴. Sam: That's right. And once you have a few ideas that meet those crit...

Generated by Bing GPT chat, with no edits.  This is a possible conversation between Paul Graham, Mark Zuckerberg, and Sam Altman where they discuss and build on each other's principles for coming up with startup ideas.  Paul: Hi Mark and Sam, thanks for joining me today. I thought it would be interesting to talk about how we approach startup ideas and what we've learned from our experiences. Mark: Sure, sounds good. I'm always curious to hear how other founders think about startups. Sam: Me too. I think there's a lot of value in sharing our perspectives and insights. Paul: Great. Well, let me start by saying that I think the way to get startup ideas is not to try to think of startup ideas. It's to look for problems, preferably problems you have yourself . Mark: I agree with that. That's how Facebook started. I wanted a way to connect with my friends at Harvard and see what they were up to. I didn't think of it as a startup idea at first. It was just somethin...

A popular friend of mine once shared a trick to liven up any gathering.  "I just make up a game." He went on to demonstrate by making up a game of throwing a crumpled piece of paper a wall and then making it land in a trash. The first to 5 wins. Three of us were then engrossed in the game of trash basketball.  Games make boring things fun. Think of any sport - cricket, soccer, football, tennis, car racing, etc. They are all pretty meaningless in a practical sense, but billions of people are engrossed in them.  That's a key idea because many important things in life, like exercising, filing taxes, learning something new, chores, working towards an idea or business, etc. have parts that are pretty mechanical and boring. They become barriers for us to doing them well and consistently, and eventually, stop us from succeeding at the important thing. You can try to use willpower or motivate yourself with the final goal, but it's tiring and often futile to resist boredom.  ...

Couple of years ago, I reached out to a smart person to see if he wanted to invest in a friend's startup.  His response was quick and confident.  "I don't invest in seed startups. It’s not a great asset class unless you have some systemic advantage like y combinator. But I appreciate your offer."  He is right. Most early stage startups fail. To win in early stage investing, you need to invest in large number of promising companies, so that a few of them can 100X and pay for all the rest. In order to do that, you need deal flow, enough capital, or a different way to pursue a portfolio approach.  The broader lesson is to first recognize when you are drawn into playing a different game in business or life, then step back and understand the nature of the game, what's needed to win that game, and decide whether you can and want to develop the skills and advantages to play and win the game.  

This is probably the most valuable question you can ask when working on anything. A very common failure mode for founders, PMs, software teams, and people in general is to try and solve poorly articulated and unsubstantiated problems. So they end up solving non-existent problems or solving them poorly.  I think this fatal error can be easily avoided with a simple framework - "Problem Stories" organized in an "Opportunity tree".   What is a Problem Story? User stories are a popular and useful tool to describe building blocks of a solution.  As a User X, I'd like Y, so that I can do Z They offer more clarity and context than just saying "build Y", and that reminds, empowers and motivates the team to build the right thing.  Problem story is exactly that, but for the problem.   As a [Person/User] A, I have [slight/significant] problem with B, because of C. Supporting by data X and/or anecdotes Y.  For example:  As a a person trying to lose w...