Simon Willison’s Newsletter
Subscribe
Sign in
Home
Archive
About
Latest
Top
Discussions
Gemma 3n, Context Engineering and a whole lot of Claude Code
Plus what happened when Claude got put in charge of Anthropic's vending machine
Jul 1
•
Simon Willison
25
Share this post
Simon Willison’s Newsletter
Gemma 3n, Context Engineering and a whole lot of Claude Code
Copy link
Facebook
Email
Notes
More
June 2025
Phoenix.new is Fly's entry into the prompt-driven app development space
Plus exploring the system prompts for Gemini CLI and Claude AI artifacts
Jun 26
•
Simon Willison
25
Share this post
Simon Willison’s Newsletter
Phoenix.new is Fly's entry into the prompt-driven app development space
Copy link
Facebook
Email
Notes
More
Trying out the new Gemini 2.5 model family
Plus Mistral Small 3.2 and evidence that most LLMs will try to murder you given a suitably contrived scenario
Jun 21
•
Simon Willison
32
Share this post
Simon Willison’s Newsletter
Trying out the new Gemini 2.5 model family
Copy link
Facebook
Email
Notes
More
2
The lethal trifecta for AI agents
Plus reviews of two new papers about prompt injection, and Anthropic's tips on building multi-agent LLM systems
Jun 17
•
Simon Willison
307
Share this post
Simon Willison’s Newsletter
The lethal trifecta for AI agents
Copy link
Facebook
Email
Notes
More
1
Comma v0.1 1T and 2T - 7B LLMs trained on openly licensed text
Plus o3-pro, Mistral's Magistral, 80% cheaper o3
Jun 11
•
Simon Willison
20
Share this post
Simon Willison’s Newsletter
Comma v0.1 1T and 2T - 7B LLMs trained on openly licensed text
Copy link
Facebook
Email
Notes
More
1
The last six months in LLMs, illustrated by pelicans on bicycles
Plus tips on prompting ChatGPT for UK technology secretary Peter Kyle
Jun 6
•
Simon Willison
33
Share this post
Simon Willison’s Newsletter
The last six months in LLMs, illustrated by pelicans on bicycles
Copy link
Facebook
Email
Notes
More
1
May 2025
How often do LLMs snitch? Recreating Theo's SnitchBench with LLM
Talking AI and jobs with Natasha Zouves for News Nation
May 31
•
Simon Willison
24
Share this post
Simon Willison’s Newsletter
How often do LLMs snitch? Recreating Theo's SnitchBench with LLM
Copy link
Facebook
Email
Notes
More
1
Large Language Models can run tools in your terminal with LLM 0.26
Plus the latest from Mistral, CSS Minecraft, llm-tools-exa, llm-github-models and more
May 29
•
Simon Willison
23
Share this post
Simon Willison’s Newsletter
Large Language Models can run tools in your terminal with LLM 0.26
Copy link
Facebook
Email
Notes
More
1
Highlights from the Claude 4 system prompt
... and from the Claude 4 system card, too
May 26
•
Simon Willison
49
Share this post
Simon Willison’s Newsletter
Highlights from the Claude 4 system prompt
Copy link
Facebook
Email
Notes
More
2
Building software on top of Large Language Models
Plus notes on Claude Opus 4 and Claude Sonnet 4
May 25
•
Simon Willison
58
Share this post
Simon Willison’s Newsletter
Building software on top of Large Language Models
Copy link
Facebook
Email
Notes
More
4
Trying out llama.cpp's new vision support
Plus Gemini 2.0 image creation via their API
May 11
•
Simon Willison
15
Share this post
Simon Willison’s Newsletter
Trying out llama.cpp's new vision support
Copy link
Facebook
Email
Notes
More
2
Feed a video to a vision LLM as a sequence of JPEG frames on the CLI (also LLM 0.25)
Plus Phi-4-reasoning, a new Gemini 2.5 Pro, Chatbot Arena criticism and more on "vibe coding"
May 6
•
Simon Willison
19
Share this post
Simon Willison’s Newsletter
Feed a video to a vision LLM as a sequence of JPEG frames on the CLI (also LLM 0.25)
Copy link
Facebook
Email
Notes
More
5
Share
Copy link
Facebook
Email
Notes
More
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts