Source

Simon Willison’s Weblog

3 items

The best single filter for the practical side of working with language models. He tries models the day they ship and writes about tools, prompts, and security holes — prompt injection above all. If you follow one blog, make it this one.

simonwillison.net ↗

Tools

llm 0.33 takes the pin out and moves to httpx2

Version 0.32.1 held fresh installs together by pinning the OpenAI Python package below 3.0.0. That was a holding action, and 0.33 does the actual repair: it upgrades to the OpenAI library 3.x and switches its HTTP client from httpx to httpx2. The release also carries changes you will notice in daily use, including a --key option on the embedding commands and server-side tool results that finally show up in llm logs.

Simon WillisonAugust 23verified

Tools

A fresh install of llm broke because the OpenAI library stopped using httpx

Version 0.32.1 pins the OpenAI Python package below 3.0.0 so that new installations work again. Nothing in llm changed to cause the break: it imported httpx while relying on the OpenAI package to bring it along, and when that package dropped httpx the dependency simply stopped arriving. It is a small release with a lesson that outlives it.

Simon WillisonAugust 22verified

Tools

ChatGPT search switched en masse to the site: operator

On August 20, Simon Willison relayed a measurement from Promptwatch showing that ChatGPT abruptly began narrowing its searches to preselected domains. The share of queries carrying the site: operator held between 0.3% and 0.5% for weeks, then jumped to 16% to 17% on August 8 — two days after OpenAI announced accuracy fixes in GPT-5.6. Willison concludes that the search tool internally has the shape search(query, recency, domains), which means the model picks domains before it even frames the question. If you care about visibility in that search, you are no longer competing only for a place in the result but for your domain to make the list the model assembles on its own.

Simon WillisonAugust 21verified