Simon Willison AI Filter

Simon Willison AI Filter August 13, 2026 19:37

Release: llm-gemini 0.33

LLM plugin to access Google's Gemini family of models

Simon Willison AI Filter August 11, 2026 22:40

Stealing Reasoning Traces from Proprietary LLM APIs

A vanity domain name (stolen-thoughts.com) for a neat paper: Anthropic, OpenAI, and Google return encrypted chain-of-thought blocks to clients that can be replayed across sessions, users, and models. We take …

Models

OpenAI Models Anthropic Google

Simon Willison AI Filter August 09, 2026 23:31

A quote from Claude Opus 5 system prompt

Claude Fable 5 and Claude Mythos 5 were first released on June 9, 2026. On June 12, 2026, Anthropic suspended access to both models to comply with U.S. Department of …

Models

Models Anthropic Claude Mythos

Simon Willison AI Filter August 08, 2026 22:36

Auto mode is now the default in Claude Code for Pro, Max, and Team plans

Anthropic are really confident in Claude Code's auto mode, to the point that they are making it the default setting for new sessions in most Claude Code plans starting on …

Models

Models Anthropic Claude Claude Code

Simon Willison AI Filter August 08, 2026 14:06

Comment: Now we have a timeline of the OpenAI accidental attack against Hugging Face

Now we have a timeline of the OpenAI accidental attack against Hugging Face

Models

OpenAI Models

Simon Willison AI Filter August 07, 2026 23:55

Now we have a timeline of the OpenAI accidental attack against Hugging Face

OpenAI gave a last-minute presentation at the Black Hat security on Wednesday about “the Hugging Face Incident” (previously on this blog). The video was published yesterday. It’s short and information …

Models

OpenAI Models

Simon Willison AI Filter May 15, 2026 00:42

Release: datasette-llm-limits 0.1a0

Plugin for configuring periodic limits on LLM usage in Datasette

Models

Simon Willison AI Filter May 12, 2026 17:45

Release: llm 0.32a2

Access large language models from the command-line

Models

Simon Willison AI Filter May 11, 2026 18:48

TIL: Using LLM in the shebang line of a script

This comment on Hacker News inspired me to investigate patterns for using my LLM CLI tool in a shebang line:

Models

Simon Willison AI Filter May 08, 2026 21:00

Using Claude Code: The Unreasonable Effectiveness of HTML

Thought-provoking piece by Thariq Shihipar (on the Claude Code team at Anthropic) advocating for HTML over Markdown as an output format to request from Claude. The article is crammed with …

Models

Models Anthropic Claude Claude Code Using Claude

Simon Willison AI Filter May 07, 2026 19:57

Release: llm-gemini 0.31

LLM plugin to access Google's Gemini family of models

Models

Models Google Gemini

Simon Willison AI Filter May 07, 2026 17:56

Behind the Scenes Hardening Firefox with Claude Mythos Preview

Fascinating, in-depth details on how Mozilla used their access to the Claude Mythos preview to locate and then fix hundreds of vulnerabilities in Firefox: Suddenly, the bugs are very good …

Models

Models Claude Mythos