Flux
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
GitHub Actions Checkout Now Blocks Risky pull_request_target Checkouts

GitHub Actions Checkout Now Blocks Risky pull_request_target Checkouts

GitHub has released actions/checkout v7 with a new default protection aimed at one of the most persistent GitHub Actions supply chain risks: privileged workflows that check out and execute code from untrusted pull requests. The change makes actions/checkout refuse common “pwn request” patterns when workflows run under pull_request_target or certain workflow_run events. These workflows execute in the context of the base repository, giving them access to the base repo’s GITHUB_TOKEN, secrets,…

Socket
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
Introducing Repository Access Permissions and Custom Roles

Introducing Repository Access Permissions and Custom Roles

Socket now supports more granular access control for organizations with Custom Roles and Repository Access Permissions, giving teams a more precise way to manage who can do what, and where they can do it. Modern engineering organizations rarely map cleanly to a single security team or a single set of repositories. A user might need to review alerts for one team's repositories, manage scans for another, or support a temporary project without gaining access to the entire organization. Access…

Socket
Building RAG in Laravel: Four Ingestion Bugs That Silently Wreck Retrieval

Building RAG in Laravel: Four Ingestion Bugs That Silently Wreck Retrieval

Every Laravel RAG tutorial builds the same ingestion pipeline (chunk, embed, store) and stops the moment the agent answers on screen. None of them check whether retrieval is any good. But retrieval quality is decided at ingestion, before the model runs once, and four decisions there fail with no error, no exception, no failed test: Chunking that severs the answer mid-sentence, so answer@1 falls while source hit@1 still looks healthy. An HNSW index built with vector_l2_ops while you query with…

Freek Van der Herten