Simon Willison AI Filter

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

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

Simon Willison AI Filter May 07, 2026 17:09

Notes on the xAI/Anthropic data center deal

There weren’t a lot of big new announcements from Anthropic at yesterday’s Code w/ Claude event, but the biggest by far was the deal they’ve struck with SpaceX/xAI to use …

Models Infrastructure

Models Infrastructure Anthropic xAI Claude SpaceX

Simon Willison AI Filter May 06, 2026 15:58

Live blog: Code w/ Claude 2026

I’m at Anthropic’s Code w/ Claude event today. Here’s my live blog of the morning keynote sessions.

Models

Models Anthropic Claude

Simon Willison AI Filter May 05, 2026 01:56

Release: datasette-llm 0.1a7

LLM integration plugin for other plugins to depend on

Models

Simon Willison AI Filter May 05, 2026 01:31

Release: llm-echo 0.5a0

Debug plugin for LLM providing an echo model

Models

Simon Willison AI Filter May 03, 2026 15:13

A quote from Anthropic

We used an automatic classifier which judged sycophancy by looking at whether Claude showed a willingness to push back, maintain positions when challenged, give praise proportional to the merit of …

Models

Models Anthropic Claude

Simon Willison AI Filter April 30, 2026 23:03

Our evaluation of OpenAI’s GPT-5.5 cyber capabilities

The UK's AI Security Institute previously evaluated Claude Mythos: now they've evaluated GPT-5.5 for finding security vulnerability and found it to be comparable to Mythos, but unlike Mythos it's generally …

Models

Simon Willison AI Filter April 29, 2026 23:52

Release: llm 0.32a1

Access large language models from the command-line

Models

Simon Willison AI Filter April 29, 2026 19:01

LLM 0.32a0 is a major backwards-compatible refactor

I just released LLM 0.32a0, an alpha release of my LLM Python library and CLI tool for accessing LLMs, with some consequential changes that I’ve been working towards for quite …

Models