Follow all of simonwillison.net →

Happy 20th birthday Django! Here's my talk on Django Origins from Django's 10th

Simon Willison’s WeblogHN
Read on Scour →
Feeds

Grok: searching X for "from:elonmusk (Israel OR Palestine OR Hamas OR Gaza)"

Simon Willison’s WeblogHN2
Read on Scour →
Feeds

Phoenix.new is Fly's entry into the prompt-driven app development space

Simon Willison’s WeblogHN
Read on Scour →
Feeds

Trying out the new Gemini 2.5 model family

Simon Willison’s Weblog
Read on Scour →
Feeds

The lethal trifecta for AI agents: private data, untrusted content, and external communication

Simon Willison’s WeblogHN3
Read on Scour →
Feeds

An Introduction to Google’s Approach to AI Agent Security

Simon Willison’s Weblog
Read on Scour →
Feeds

Design Patterns for Securing LLM Agents against Prompt Injections

Simon Willison’s WeblogHN
Read on Scour →
Feeds

Comma v0.1 1T and 2T - 7B LLMs trained on openly licensed text

Simon Willison’s WeblogHN
Read on Scour →
Feeds

The last six months in LLMs, illustrated by pelicans on bicycles

Simon Willison’s WeblogHN2
Read on Scour →
Feeds

Tips on prompting ChatGPT for UK technology secretary Peter Kyle

Simon Willison’s Weblog
Read on Scour →
Feeds

How often do LLMs snitch? Recreating Theo's SnitchBench with LLM

Simon Willison’s WeblogHN
Read on Scour →
Feeds

Talking AI and jobs with Natasha Zouves for News Nation

Simon Willison’s Weblog
Read on Scour →
Feeds

Large Language Models can run tools in your terminal with LLM 0.26

Simon Willison’s WeblogHN
Read on Scour →
Feeds

Highlights from the Claude 4 system prompt

Simon Willison’s WeblogHN2
Read on Scour →
Feeds

Live blog: Claude 4 launch at Code with Claude

Simon Willison’s WeblogHN
Read on Scour →
Feeds

I really don't like ChatGPT's new memory feature

Simon Willison’s WeblogHN
Read on Scour →
Feeds

Building software on top of Large Language Models

Simon Willison’s WeblogHN2
Read on Scour →
Feeds

Trying out llama.cpp's new vision support

Simon Willison’s WeblogHN
Read on Scour →
Feeds

Saying "hi" to Microsoft's Phi-4-reasoning

Simon Willison’s Weblog
Read on Scour →
Feeds

Feed a video to a vision LLM as a sequence of JPEG frames on the CLI (also LLM 0.25)

Simon Willison’s Weblog
Read on Scour →
Feeds

Keyboard shortcuts

Navigation

Next / previous post
j/k
Open post
oorEnter
Preview post
v

Post actions

Love post
a
Like post
l
Dislike
d
Undo reaction
u
Save / unsave
s

Recommendations

Add interest / feed
Enter
Not interested
x

Go to

Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Discover
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help