Nano Banana 2 Lite
Nano Banana 2 Lite Also known as Gemini 3.1 Flash Lite Image (gemini-3.1-flash-lite-image in their API), this is the 'fastest and cheapest Gemini image model, engineered for velocity and scale'. I use
Knowledge catalogue
Nano Banana 2 Lite Also known as Gemini 3.1 Flash Lite Image (gemini-3.1-flash-lite-image in their API), this is the 'fastest and cheapest Gemini image model, engineered for velocity and scale'. I use
Notes (and a Pelican) on Claude Sonnet 5 - the new tokenizer makes it ~1.4x more expensive for English, ~1.33x more expensive for Spanish but roughly the same price for Simplified Mandarin https://sim
shot-scraper is a command-line utility for taking automated screenshots of websites . It is designed primarily for documentation but also has scraping applications . The 1.10 release likely includes u
The AI Compass This political compass style quiz by bambamramfan is pretty neat - answer 29 questions about AI and AI ethics to see which of the 30 archetypes you best fit. I'm impressed that my answe
We’ve received notice that the Department of Commerce has lifted export controls on Claude Fable 5 and Mythos 5. We'll begin restoring access tomorrow, and will share an update soon. We’re grateful to
What's new in Claude Sonnet 5 Claude Sonnet 5 came out this morning. I always head straight for the 'what's new' developer docs because they tend to have more actionable information than the official
Tool: HTML table extractor Yet another in my growing collection of paste-conversion tools. This one accepts pasted rich text from browsers (with embedded HTML tables) and converts every detected table
Ornith-1.0: Self-Scaffolding LLMs for Agentic Coding This is an interesting new open weights (MIT licensed) model, the first model release from DeepReinforce. [...] with variants including 9B Dense, 3
Hack Your Summer I learned about this initiative from DJ Patil this morning: It’s a 4-week, high-velocity production sprint for undergraduate students, graduate students, and recent graduates who want
Human Agent in the loop I dislike the phrase “human in the loop” because it cedes authority to the machines. Let’s flip the narrative. It’s our loop, we work the same way we always have, now we recrui
Incident Report: CVE-2026-LGTM Spectacular hypothetical incident report by Andrew Nesbitt. Day 2, 16:00 UTC --- Two AI review agents from competing vendors, both attached to a downstream pull request
Is it just me, or are today's LLMs less likely to default to building everything in React than they were last year? I used to have to say 'don't use React' in almost all of my frontend web dev prompts
Not sure if that's a change in default preferences from the models or just that I'm often prompting inside existing projects and the models know full well not to introduce React to a project that isn'
This is a bad state of affairs. Consider, in particular, some industry dynamics: Frontier models are trained at an enormous cost, and a significant fraction of that cost is recouped in the few post-re
We're beginning a limited preview of the GPT‑5.6 series: Sol, our flagship model; Terra, a balanced model for everyday work; and Luna, a fast and affordable model. Terra has competitive performance to
This is like saying there's no learning curve to being a manager because your employees will just do whatever you tell them to do. — Timothy B. Lee, on the idea that LLMs take no skill and have no lea
This statement is a critical analogy about dismissing learning curves in technology or professional contexts. Simon Willison uses the comparison to highlight how unrealistic expectations—assuming empl
What happened after 2,000 people tried to hack my AI assistant Fernando Irarrázaval ran a challenge on hackmyclaw.com to see if anyone could leak secrets held by his OpenClaw test instance by sending
AI and Liability Bruce Schneier on the recent German ruling that Google be held liable for errors introduced in their AI overviews: AI agents are agents of the person or organization that deploys them
Also not a great advertisement for a sandboxing product: @daytonaio effectively saying they don't trust the security of their product enough to expose the source code When the competition for sandboxe
Release: datasette-export-database 0.3a2 An embarrassingly tiny release. The pyproject.toml had pinned to datasette==1.0a27, inadvertently making this plugin incompatible with all other Datasette vers
Update: it's fixed! @simonw @ClaudeDevs @claudeai This is fixed — the egress proxy was incorrectly blocking git/gh reads to public repos that weren't attached to the session. Clones/fetches work again
Claude Code for web just started saying 'GitHub is blocked by egress policy', which is a big problem for me because most of my prompts there start with things like 'clone simonw/sqlite-utils to /tmp t
In the last few months, I've started to see [job applications] that were clearly cowritten by an LLM, link to an LLM-generated portfolio site, which then links to LLM-generated GitHub projects, with p
This entry references a Claude.ai coding session shared by Simon Willison, a well-known technology writer and open source developer, likely demonstrating a practical example of using Claude's code int
simonw/browser-compat-db Inspired by Mozilla's new MDN MCP service - source code here - I decided to try converting their comprehensive mdn/browser-compat-data repository full of browser compatibility
... and now you can buy your own! https://happy-pelicans.printify.me/product/29480311 Proceeds go to http://birdrescue.org, a local non-profit that rescues pelicans (among other birds) I printed a cus
Release: datasette 1.0a35 I'll write more about this one tomorrow, but it's a big release. Three highlights from the release notes: New 'Create table' interface in the database actions menu, backed by
Tool: OPFS + Pyodide test harness I've been pondering if Datasette Lite - the Python Datasette application run entirely in the browser using Pyodide and WebAssembly - might be able to edit persistent
Pamela rocks https://x.com/pamelafox/status/2069183465501921605 By popular demand, here's a lil store where you can buy your own: https://happy-pelicans.printify.me/product/29480311 I will donate proc
This post highlights an interactive web-based demo of the Moebius model, which users can test directly in their browser with approximately 1.3GB of model data downloaded locally. The tool appears to b
Pamela Fox created a custom t-shirt design referencing Simon Willison's Pelican benchmark, a technical tool or metric in web development or performance testing. She posted about it on X (formerly Twit
My parallel agent side-project today was having Claude Code port the new Moebius image pinpointing model to ONNX in order to run it entirely in the browser https://simonwillison.net/2026/Jun/22/portin
This morning on Hacker News I saw Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance, describing a small but effective inpainting model - a model where you can mark region
I just released the first release candidate for sqlite-utils v4, adding a migrations system (previously released independently as sqlite-migrate) and support for nested transactions: https://simonwill
sqlite-utils is my combined Python library and CLI tool for working with SQLite databases. It provides an extensive set of higher-level operations on top of Python's default sqlite3 package, including
Temporary Cloudflare Accounts for AI agents The announcement says this is 'for AI agents' but (as is pretty common these days) the AI hook isn't really necessary, this is an interesting feature for ev
The real valuable capability MCP offers over skills/CLI is isolating the auth flow outside of the agent’s context window, and potentially out of the harness completely. [...] Maybe the idealized form
Anthropic Walks Back Policy That Could Have ‘Sabotaged’ AI Researchers Using Claude Big scoop for Maxwell Zeff at Wired: “We’re changing Fable 5’s safeguards for frontier LLM development to make them
Don't miss the exact text though: 'We’re changing Fable 5’s safeguards for frontier LLM development to make them visible' - make them visible means they're undoing the truly egregious (dare I say 'una
Release: datasette-agent 0.2a0 Highlights from the release notes: Tools can now ask the user questions mid-execution. Tools that declare a context parameter receive a ToolContext object, and await con
DiffusionGemma Last May Google briefly released an experimental Gemini Diffusion model. I tried the preview at the time and recorded it running at 857 tokens/second. It was an exciting model, but Goog
Simon Willison demonstrated Fable's pelican illustrations generated at different Claude API thinking effort levels, showcasing how increased computational investment affects output quality and cost. T
If Claude Fable stops helping you, you'll never know Jonathon Ready highlights one of the more eyebrow-raising details from the 319 page system card for Fable 5 and Mythos 5. Here's a longer excerpt,
Easy solution to slow down recursive AI self improvement: The lab with the top-ranked model must agree THEY must not use it for working on frontier AI But everyone else should have access to it. By de
Wrote up my initial impressions of Claude Fable 5 - it has a big model smell: slow, expensive and capable of crunching through pretty much everything I threw at it https://simonwillison.net/2026/Jun/9
A TIL on using http://agentsview.io to calculate token spending with Claude Fable 5 despite that model not yet being included in the AgentsView pricing database https://til.simonwillison.net/llms/agen
BREAKING: Anthropic just dropped Claude Fable 5—this is Mythos, made safe for public release. It is the best coding model in the world. We've been testing it internally @every for the last week or so
I didn't have early access to today's Claude Fable 5 release, but I've spent the past ~5.5 hours putting it through its paces. My initial impressions are that this is something of a beast. It's slow,
I've had access to Fable for a bit. A genuine jump in capability, I could feed it a 15 page design document for a project and it would work for 9+ hours and deliver terrific results. But working with
I feel a lot of things changing as working software increasingly comes out on a tap. The Jevon's paradox kicks in and I feel my own demand for software growing substantially. You can ask for anything
TIL: Setting a custom price for a model in AgentsView I've been really enjoying AgentsView by Wes McKinney as a tool for exploring my token usage across different coding agents running on my laptop. C
Given how badly burned anyone who took Apple's 2024 WWDC Apple Intelligence announcements at face value was, I'm holding to a strict 'I'll believe it when I see it' policy for everything they announce
That's both OpenAI and Anthropic with confidential S-1s filed with the SEC - Anthropic filed theirs on June 1st We recently submitted a confidential S-1. We expect it to leak so we’re just announcing
Release: datasette-agent-edit 0.1a0 I'm planning several plugins for Datasette Agent which can make edits to existing pieces of text - things like collaborative Markdown editing, updating large SQL qu
I may have finally found the Python-in-a-sandbox solution I've been looking for... here's my latest experiment, this time running MicroPython in WebAssembly inside my Python applications https://simon
Release: micropython-wasm 0.1a2 I added a CLI to micropython-wasm (issue #7), inspired by the first draft of the blog entry when I realized it would be a great way to illustrate the Try it yourself se
I've been experimenting with different approaches to running code in a sandbox for several years now, but my latest attempt feels like it might finally have all of the characteristics I've been lookin
This post demonstrates how to run MicroPython compiled to WebAssembly using the `uvx` tool with a simple command-line example that prints 'Hello world'. It showcases the ease of executing MicroPython
OpenAI Help: Lockdown Mode OpenAI first teased this in February, but now it's live and 'rolling out to eligible personal accounts, including Free, Go, Plus, and Pro, and self-serve ChatGPT Business ac