Hey, it’s John.

An Anthropic and Menlo Ventures Hackathon Project On November 2, I went to a Claude Hackathon hosted at the Anthropic HQ. I had worked on this project before, but it was a good chance to finish and demo it to others! Large language models are smart, and immensely helpful. Oftentimes, I find that my progress on a problem is bottlenecked more by my ability to maintain a continuous stream of uninterrupted focus, rather than intelligence....

https://philosophy-chat.com/ Over the last few months, I’ve been working on a Q&A application for academic philosophy questions. I now have V1 deployed on the web! Please be patient, as it commonly fails after the first question and the runtime is ~10 seconds per question. But it works, and I’m proud of it. This project was motivated by 1) my desire to personally use the site as a way to deepen my knowledge of philosophy and 2) as a proof-of-concept LLM application that can give sources and make up wrong information less....

London is the greatest city in the world, and a lovely place to travel to for any length of time. I was lucky to live and study there for a bit more than a year, and often get questions about travel recommendations. After writing a close friend a lengthy message, I thought it’d be best to write a complete document to share to others who ask. Things that London does well London has particularly good offerings in the following categories....

A lot of people who I look up to in tech have websites like this, where they talk about themselves a bit more than they’d be comfortable doing outside of interviews. I also wanted a place to write random thoughts, and I suppose that people in hiring positions look favorably on things like this. So, it was time to make a website again. I was aiming for the following: Easy to add writings in markdown format Quick to push updates Not using a website-making-website I’d done this before, using Bootstrap and AWS, but found the AWS experience pretty frustrating....

Large Language Models (LLMs) refer to entities like ChatGPT, or the variety of competitors that have emerged recently. These are massive machine learning models made on transformer architectures, trained on mind-numbingly large sets of text, and fine-tuned with human feedback. They end up being pretty good at writing and reading as a result. Recently, they’ve become quite useful in conversation about a ton of topics, technical and personal. One capability that LLMs are documented at excelling at is, when prompted, giving convincing statements about their “consciousness”....

The full 10,000 word document can be downloaded from my Github here Abstract As algorithmic decisions continue to play increasingly consequential roles in our lives, it is reasonable that we are offered explanations in some cases. First, then, there must be an account of algorithmic explanation to evaluate if something is an explanation, and the quality evaluated thereafter. Most accounts of explainable artificial intelligence offer a somewhat narrow view– a specific explanation type or mechanism, which by itself doesn’t seem to be a general account....

An ongoing list of disjoint thoughts that are worth writing down. Some are old. Deep Okay-ness Based off my recent interest in meditation and a blog post from Sasha Chapin, I’ve been thinking about the feeling that many describe as a feeling of “deep okay-ness”, “persistent self love” or “ambient feeling of good”. I think this ought to be the primary goal of most peoples lives– to have a feeling of good that is independent of external circumstances....