标签：#r

AI coding agents are getting very good at writing code. They can build components, create APIs, fix bugs, and implement features from short prompts. But I kept noticing one issue: Working code does not always mean a good product. For example, if you ask an agent: “Add a delete button to every project.” It may technically do exactly that. But will it also think about: confirmation before deletion error handling undo options accessibility clear feedback to the user Those are not just coding problems. They are product judgment problems. That led me to experiment with a reusable instruction layer for AI coding agents at AudranLab. The idea is simple: Instead of only asking an agent, “Can you build this?”, also encourage it to ask, “Is this a good way to build it?” I want agents to consider things like accessibility, failure states, destructive actions, usability, and sensible defaults while they work. This does not magically turn an AI into a product designer. But I think it raises an interesting question: Can explicit product principles consistently improve the quality of software generated by coding agents? That is what I’m currently exploring. My next step is to test the approach across different coding tasks and compare the results with and without the additional product-judgment layer. If you’re interested in AI agents, LLM reliability, developer tools, or applied AI, I’ll be sharing more experiments here. AudranLab: https://www.audrantechlab.online/

Neocloud Lambda has raised $1B in private debt to buy Nvidia AI chips and lease them to Microsoft. It's the latest in a string of loans, underscoring the high cost of the AI boom.

I often find interesting things in Hacker News posts and comments, but threads are often long and take a lot of time to go through. I built Rundown for this. It's a cross-platform desktop app with Claude Code and Codex integration that gives me a rundown of the post and comments, with links back to the comments it pulled each bit from. I can also chat with the post or the entire thread.

The longtime far-right operator and troll, a UK citizen, is being held in ICE custody pending his removal from the United States.

Given 10 benchmarks for specific misaligned behaviors, the automated systems were able to improve performance on every single one without degrading overall performance.

I have been working on Sesame, an open-source password manager that keeps your vault local by default. You don't need an account to create or use a vault, and the hosted service never receives the vault itself. It's still early software and the independent security review isn't finished yet, so I am mainly interested in feedback, testing, and people looking through the code. (Linux support is yet to be released on v0.1.2, but currently is in the works.)

Hi HN, I built Boop because I wanted application events sent directly to my phone without paying for another service or routing everything through Slack or Telegram. Boop is a small, open-source server paired with an open-source iOS app. The server currently uses around 8 MB of memory on my machine. It’s deliberately not an observability platform or a replacement for Sentry. It receives events from your applications, sends native push notifications, and keeps them in a purpose-built mobile inbox