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 section. Tags: python, sandboxing, webassembly, micropython
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 looking for. I've released it as an alpha package called micropython-wasm, and I'm using it for a code execution sandbox plugin for Datasette Agent called datasette-agent-micropython. Why do I want a sandbox? What I want from a sandbox WebAssembly looks really promising here MicroPython in WebAssembly…
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 accounts": Lockdown Mode is designed to help prevent the final stage of data exfiltration from a prompt injection attack by limiting outbound network requests that could transfer sensitive data to an attacker. Lockdown Mode does not prevent prompt injections from appearing in the content ChatGPT…
Full hands-on video walkthrough.
On this week’s episode, host and the founder of AI advisory firm Intelligence Briefing Andreas Welsch brought together Maya Mikhailov, cofounder and CEO of Savvi AI, and Doug Shannon, generative AI and intelligent automation leader, to cover a handful of interconnected topics that practitioners are navigating right now: OpenAI’s push into personal finance, the role […]
We will no longer accept public pull requests. [...] A substantial patch used to imply substantial effort, and that effort was a reasonable proxy for good faith. That assumption no longer holds. [...] Whether code was typed by hand is beside the point. What matters is who is responsible for it once it enters the browser. Ladybird is becoming a browser for real users. The people introducing changes to it must be the people who decide those changes belong in the project, and who will answer for…
I set up an AI agent on a rented GPU, pointed it at a training script, and went to bed. By morning it had run 40 experiments, improved validation loss by 5.9%, and cut memory usage from 44 GB to 17 GB. It also spent four hours chasing a bug that a linter introduced behind […]
AI enthusiasts are in a race against time, AI skeptics are in a race against entropy Charity Majors neatly captures the dynamic between AI enthusiasts and AI skeptics, both of whom are trying to build great software, often in the same teams: The enthusiasts are not wrong. We are starting to see real, non-imaginary, discontinuous leaps in capabilities from teams that lean in hard to working with AI. And this does not feel like a normal technology cycle where you can wait for the dust to settle;…
(without compromising accuracy)
After this story was published Google's spokesperson reached out and asked us to publish a slightly different version of that statement. The new statement no longer stated that "it's critical that we maintain humans in the loop." — Emanuel Maiberg, 404 Media, Google Employees Internally Share Memes About How Its AI Sucks Tags: ai-ethics, journalism, ai, google
DJ Patil has spent the past several months on a listening tour. Wherever he travels, he finds a local university, pings faculty and students and anyone else who wants to show up, and runs an AMA. He’s heard from grad students who can’t get callbacks, hospital administrators dealing with federal policy changes that land like […]
A third of the way into a security-operations guide that Anthropic published in April 2026, wedged between a recommendation to patch CISA’s Known Exploited Vulnerabilities list and a suggestion to automate your deployment pipeline is a small recommendation: “Use EPSS to prioritize the rest.” For anyone who has worked on a vulnerability backlog in the […]
Naive RAG → Retrieval layer → Agentic Layer
Uber Caps Usage of AI Tools Like Claude Code to Manage Costs I wrote the other day about Uber blowing its 2026 AI budget in four months, and how that wasn't particularly surprising given they would have set that budget in 2025, before anyone could have predicted how popular token-burning coding agents were about to become. Natalie Lung for Bloomberg: The rideshare giant is limiting all employees to $1,500 in monthly token spending per AI coding tool, an Uber spokesperson said in response to a…
As syntax becomes cheap and abundant, architectural control becomes the scarce resource. Effective governance starts upstream, where intent, constraints, and threat models shape the agent’s working context before generation begins. The goal isn’t better prompting but build-time boundaries that prevent structurally invalid code from entering the system. The Frankenstein factories The dark factories (as Dan […]