Scaling LLMs to Larger Codebases
This is the third part of a series on LLMs in software engineering. First we learned what LLMs and genetics have in common. (part 1) LLMs don’t improve all facets of engineering. So, understanding which areas LLMs do improve (part 2) is important for knowing how to focus our investments. (part 3) How do we […]
Origin of Hallucination in LLMs, The physical source of hallucinations has found
Abstract:Large language models (LLMs) frequently generate hallucinations — plausible but factually incorrect outputs — undermining their reliability. While prior work has examined hallucinations from macroscopic perspectives such as training data and objectives, the underlying neuron-level mechanisms remain largely unexplored. In this paper, we conduct a systematic investigation into hallucination-associated neurons (H-Neurons) in LLMs from three […]
Lua 5.5
Lua: version history Here is a chronology of the versions of Lua. The evolution of Lua is documented in a paper presented at HOPL III, the Third ACM SIGPLAN History of Programming Languages Conference, in 2007. See also its continuation published in 2025 in a journal. The source code and documentation for all releases of Lua […]
One year of keeping a tada list
A tada list, or to-done list, is where you write out what you accomplished each day. It’s supposed to make you focus on things you’ve completed instead of focusing on how much you still need to do. Here is what my tada lists look like: I have a page for every month. Every day, I […]
Animating Quines for Larva Labs
“Quine” by Larva Labs A couple months ago, when I was first planning to go independent again, I ran into my friend, John Watkinson, on the walk home from my studio. John is half of Larva Labs along with my good friend, Matt Hall, and they’re responsible for industry-defining projects, like CryptoPunks and Autoglyphs. I […]
Project Vend: Phase Two
In June, we revealed that we’d set up a small shop in our San Francisco office lunchroom, run by an AI shopkeeper. It was part of Project Vend, a free-form experiment exploring how well AIs could do on complex, real-world tasks. Alas, the shopkeeper—a modified version of Claude we named “Claudius”—did not do particularly well. […]
Italian Competition Authority Fines Apple $115M for Abusing Dominant Position
Search
Tachyon: High frequency statistical sampling profiler
The profiling.sampling module, named Tachyon, provides statistical profiling of Python programs through periodic stack sampling. Tachyon can run scripts directly or attach to any running Python process without requiring code changes or restarts. Because sampling occurs externally to the target process, overhead is virtually zero, making Tachyon suitable for both development and production environments. What […]
If You Don’t Design Your Career, Someone Else Will
A client once responded to one of my questions by saying, “Oh Greg, I am too busy living to think about life!” His off-the-cuff comment named a trap all of us fall into sometimes. In just one example, it is easy to become so consumed in our careers we fail to really think about our careers. To avoid this […]
A year of vibes
written on December 22, 2025 2025 draws to a close and it’s been quite a year. Around this time last year, I wrote a post that reflected on my life. Had I written about programming, it might have aged badly, as 2025 has been a year like no other for my profession. 2025 Was Different […]