· Standard
G
llmstxt.info directory · Standard
Giles' blog
Community listing
llms.txt reachable
AI Impact Score 95/100 · A
Giles' blog is listed in the llmstxt.info directory as an AI-discoverable organization. Industry: Websites & Publishers. The website www.gilesthomas.com provides its llms.txt at https://www.gilesthomas.com/llms.txt. Listed since 2 April 2026.
llms.txt address
https://www.gilesthomas.com/llms.txt
Under GDPR Art. 17 you can request the deletion of your data. Report a legal violation (Art. 16 DSA) →
llms.txt — current content
Open ↗
# Giles' Blog
> Giles' Blog is the personal technical blog for Giles Thomas, a software engineer
> and entrepreneur. Current information about Giles Thomas can be found on the
> [about page](https://www.gilesthomas.com/about.md).
This page lists the 20 most recent posts, and then all categorised posts by their
category (many posts have multiple categories).
## Recent posts
* [Adding diagrams to my static site generator with D2](https://www.gilesthomas.com/2026/08/adding-d2.md) posted on 2026-08-25T23:00:00+00:00
* [Use the built-in GELU, don't roll your own!](https://www.gilesthomas.com/2026/08/built-in-gelu.md) posted on 2026-08-20T02:00:00+00:00
* [A quick(ish) Chinchilla check](https://www.gilesthomas.com/2026/08/chinchilla-check.md) posted on 2026-08-07T19:00:00+00:00
* [How I use AI on this blog](https://www.gilesthomas.com/2026/07/ai-use.md) posted on 2026-07-31T19:00:00+00:00
* [Why do OpenAI's GPT-2 weights beat mine? Part three: testing overtraining](https://www.gilesthomas.com/2026/07/why-do-openai-gpt2-weights-beat-mine-3-overtraining.md) posted on 2026-07-31T01:15:00+00:00
* [Why do OpenAI's GPT-2 weights beat mine? Part two: the bugfix](https://www.gilesthomas.com/2026/07/why-do-openai-gpt2-weights-beat-mine-2-the-bugfix.md) posted on 2026-07-30T19:00:00+00:00
* [Why do OpenAI's GPT-2 weights beat mine?](https://www.gilesthomas.com/2026/07/why-do-openai-gpt2-weights-beat-mine-1-intro.md) posted on 2026-07-29T15:30:00+00:00
* [Benchmarking Qwen 3.6 35B MoE
[…truncated]