Flux
Couleur d'accent
Stop Getting Good at Protocols. Get Good at Agent Experience.

Stop Getting Good at Protocols. Get Good at Agent Experience.

In 2025, if you weren’t building with MCP, you weren’t serious about agents. The Model Context Protocol dominated the agent conversation for the better part of the year. Conference talks, roadmaps, hiring plans, all of it revolved around MCP. Then late 2025 into 2026, AI Skills arrived and the backlash was immediate. Engineers declared MCP […]

O'Reilly Radar — AI/ML
datasette 1.0a35

datasette 1.0a35

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 the /<database>/-/create JSON API. It can define columns, primary keys, custom column types, NOT NULL constraints, literal defaults, expression defaults and single-column foreign keys. (#2787) New "Alter table" table action and /<database>/<table>/-/alter JSON API for changing…

Simon Willison's Weblog
OPFS + Pyodide test harness

OPFS + Pyodide test harness

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 SQLite files stored on the user's computer. That's what OFPS (Origin Private File System) is for, so I had Claude Code for web build me this playground UI to try it out in different browsers. Tags: browsers, pyodide, datasette-lite

Simon Willison's Weblog
Principal Drift

Principal Drift

Over the past year I’ve reviewed enterprise agent architectures at roughly two dozen organizations, including banks, retailers, healthcare systems, and a couple of regulators. The architecture diagrams have been reliably impressive. There are boxes for the MCP gateway, the tool registry, the vector store, the orchestrator, the policy engine, and the observability stack. There are […]

O'Reilly Radar — AI/ML
Prompt Injection as Role Confusion

Prompt Injection as Role Confusion

Prompt Injection as Role Confusion First, I absolutely love this: This is a blog-style writeup of the paper. I wish every paper would come with one of these. Academic writing is pretty dry - the impact of a paper can be so much higher if you publish a readable version to accompany the formal one. Charles Ye, Jasmine Cui, and Dylan Hadfield-Menell present some fascinating research into the challenge of having models distinguish their own privileged text (here wrapped in role tags like…

Simon Willison's Weblog
Porting the Moebius 0.2B image inpainting model to run in the browser with Claude Code

Porting the Moebius 0.2B image inpainting model to run in the browser with Claude Code

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 regions of an image to remove and the model imagines what should fill the space. The released model required PyTorch and NVIDIA CUDA, but since it described itself as 0.2B I decided to try and get it running using WebGPU in a browser. TL;DR: I got it working, and you can try the demo at…

Simon Willison's Weblog
Loop Engineering

Loop Engineering

The following article originally appeared on Addy Osmani’s blog and is being reposted here with the author’s permission. Loop engineering is replacing yourself as the person who prompts the agent. You design the system that does it instead. A loop here can be thought of as a recursive goal where you define a purpose and […]

O'Reilly Radar — AI/ML
sqlite-utils 4.0rc1 adds migrations and nested transactions

sqlite-utils 4.0rc1 adds migrations and nested transactions

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 support for complex table transformations, automatic table creation from JSON data and a whole lot more. I released sqlite-utils 4.0rc1, the first release candidate for sqlite-utils v4. The major version bump indicates some (minor) backwards incompatible changes, so I'm interested in having people…

Simon Willison's Weblog
Temporary Cloudflare Accounts for AI agents

Temporary Cloudflare Accounts for AI agents

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 everyone else as well. Short version: you can now create a Cloudflare Workers project and run this, without even creating a Cloudflare account: npx wrangler deploy --temporary Cloudflare will deploy the application to a new, ephemeral project which will stay live for 60 minutes. I had GPT-5.5 xhigh…

Simon Willison's Weblog
Quoting Sean Lynch

Quoting Sean Lynch

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 of MCP is just an auth gateway for the API and nothing else. That’d still be a win. — Sean Lynch, comment on Hacker News Tags: model-context-protocol, llms, ai, generative-ai, skills

Simon Willison's Weblog
Datasette Apps: Host custom HTML applications inside Datasette

Datasette Apps: Host custom HTML applications inside Datasette

Today we launched a new plugin for Datasette, datasette-apps, with this launch announcement post on the Datasette project blog. That post has the what, but I'm going to expand on that a little bit here to provide the why. The TL;DR Datasette Apps are self-contained HTML+JavaScript applications that run in a tightly constrained <iframe> sandbox hosted on your Datasette application. They can use JavaScript to run read-only SQL queries against data in Datasette, and can run write queries too…

Simon Willison's Weblog
Esc