FeedCity

Just Talk To It - the no-bs Way of Agentic Engineering Peter Steinberger's long, detailed description of his current process for using Codex CLI and GPT-5 Codex. This is information dense and full of actionable tips, plus plenty of strong opinions about the differences betwe...

OR: The triple-decker fallacy

A local supercomputer between the size of a Mac mini and a Mac mini.

nanochat Really interesting new project from Andrej Karpathy, described at length in this discussion post. It provides a full ChatGPT-style LLM, including training, inference and a web Ui, that can be trained for as little as $100: This repo is a full-stack implementation o...

Architectural Control at Agent Velocity

Living intentionally in a world of distraction.

Today's links How to fix the UK housing crisis: Reconverting homes to human rights, rather than assets. Hey look at this: Delights to delectate. Object permanence: Theme park privacy; 3 strikes dead in Eire; HK ghost posters; Hotel wifi sucks; Facebook pays no UK tax; Econ re...

Tons of words have been written about the Trump Administrations war on Science in Universities. But few people have asked what, exactly, is science? How does it work? Who are the scientists? What do they do? And more importantly, why should anyone (outside of universities) care? (Unfortunately, you won’t see answers to these questions in […]

Onze overheid heeft regels opgesteld voor hun gebruik van de cloud, AI en andere algoritmes. En ze houden zich er bijna nooit aan. Dit wordt keer op keer vastgesteld, zoals door de Algemene Rekenkamer, waar men constateerde dat voor twee-derde van de overheids IT-projecten “in de cloud” in het geheel geen risicoafweging was gemaakt. Dus niet dat de risicoafweging niet goed was, nee, hij was er gewoon niet. Maar wel verplicht.

Slashdot: What's the reason OneDrive tells users this setting can only be turned off 3 times a year? (And are those any three times — or does that mean three specific days, like Christmas, New Year's Day, etc.)

[Microsoft's publicist chose not to answer this question.]

— Slashdot, asking the obvious question

Tags: slashdot, ai-ethics, ai, microsoft

Pretty sure this will end up as one of my longest-term restoration projects, but I'm back in the Southern Hemisphere for a little while to visit my wife's side of the family and giving me another opportunity to see if we can make progress on our defective PAL 128DCR, my fa...

This week's video was recorded on Friday morning Aussie time, and as promised, hackers dumped data the following day. Listening back to parts of the video as I write this on a Sunday morning, pretty much what was predicted happened: data was dumped, it included Qantas, and the

I built a tracker to monitor the growth of MCP servers in the wild - turns out the ecosystem is growing faster than I expected

Claude Code includes the ability to run sub-agents, where a separate agent loop with a fresh token context is dispatched to achieve a goal and report back when it's done. I wrote a bit about how these work in June when I traced Claude Code's activity by intercepting its API ...

The world's largest and most disruptive botnet is now drawing a majority of its firepower from compromised Internet-of-Things (IoT) devices hosted on U.S. Internet providers like AT&T, Comcast and Verizon, new evidence suggests. Experts say the heavy concentration of infected devices at U.S. providers is complicating efforts to limit collateral damage from the botnet's attacks, which shattered previous records this week with a brief traffic flood that clocked in at nearly 30 trillion bits of data per second.

Jeremy imagines a scenario where you’re trying to understand how someone cut themselves with a blade. It’d be hard to know how they cut themselves just by looking at the wound. But if you talk to the person, not only will you find out the reason, you’ll also understand thei...

Vibing a Non-Trivial Ghostty Feature Mitchell Hashimoto provides a comprehensive answer to the frequent demand for a detailed description of shipping a non-trivial production feature to an existing project using AI-assistance. In this case it's a slick unobtrusive auto-updat...

I'm beginning to suspect that a key skill in working effectively with coding agents is developing an intuition for when you don't need to closely review every line of code they produce. This feels deeply uncomfortable!

Tags: vibe-coding, coding-agents, ai-assisted-programming, generative-ai, ai, llms

Today's links The curious, intertwined history of climate and digital rights activism: It's going much [better|worse] than expected. Hey look at this: Delights to delectate. Object permanence: Bricked EVs; Cross-stitched tracert. Upcoming appearances: Where to find me. Recent...