Using a UI is a form of deductive reasoning that takes effort.

I recently shared some observations about trying to use generative AI tools at work and shared the experience on LinkedIn.

I hear it often enough that it seems like a commonly held belief that anxiety somehow improves performance at work and gives one an edge.

Here are the most useful metrics I’ve found for running a startup.

This note does not have a description yet. Links to this note LLM Latency Is Output-Size Bound

As it stands today, LLM applications have noticeable latency but much of the latency is output-size bound rather than input-size bound.

Most of my tasks and projects are organized using org-mode. I was looking for a way to query them from an LLM and, rather than recreate an index and a database, I can use what I normally use, org-ql using emacs in batch mode.

A recent study from Stanford found that LLM’s (GPT-4) and RAG-based AI tools (Lexis+ AI, Westlaw AI-Assisted Research, Ask Practical Law AI) hallucinate answers 16% to 40% of the time in benchmarking queries.

The way to make everything in your codebase twice as complicated is to make data nullable.

While I don’t write code every day, I find it incredibly convenient.

Sometimes using Emacs you want to know what variables are being set in the current buffer.

I recently needed to change the behavior of a library (org-download) based on the tags of the current buffer.

Many vector databases can find the top k most similar results to a query but are unable to sort by other document metadata.

Alfred does not have a mobile application that can make snippets available from your desktop to your phone.

One of the difficult parts of applying AI to existing processes and products is that people aren’t calibrated on what generative AI can and can’t do.

Writing a specification with sufficient detail to know exactly what software one should build is as much work as writing the code itself.

When asked to draw a random number between 1 and 10 and any color, most people choose the number seven and the color blue.

I want to be able to use generative AI in spreadsheets to solve unique problems.

When selling a B2B SaaS product to a wide range of company sizes (e.

Selling something is already difficult enough but when you have to sell the problem first, it’s even hRder.

A lot of startups have a business model which roughly equates to: put a dollar in, get two dollars out.

Global crises happening all at once re-inforce one another making the effects larger than any individual crisis alone.

In an episode of Boy Meets World, Shawn is in a competition of who can wait longest on a billboard suspended high up in the air in order to win tickets to the Super Bowl.

The other day I noticed a tweet from Justin Duke which outlined a plan to get his company’s codebase ready for Devin—a programming focused generative AI product.