A compact digest of model releases, papers, agentic systems, coding automation, infra, security, and high-signal developer discourse. Feed candidates are ranked locally; the scheduled Hermes worker can add qualitative synthesis.
To my knowledge, this is the first formally verified implementation of a 3D constructive solid geometry (CSG) operation: mesh intersection, implemented in Lean 4 and verified against a concise specification that pins down the surface of the resulting mesh exactly and guarantees practical well-formedness conditions on the triangulation. This project is als…
Article URL: https://fermisense.com/when-machines-take-the-wheel/ Comments URL: https://news.ycombinator.com/item?id=49078454 Points: 261 # Comments: 88
Article URL: https://spawn-queue.acm.org/doi/10.1145/3819083 Comments URL: https://news.ycombinator.com/item?id=49081644 Points: 76 # Comments: 40
Article URL: https://jfrog.com/blog/jfrog-and-openai-collaboration-on-zero-day-security-findings/ Comments URL: https://news.ycombinator.com/item?id=49082550 Points: 27 # Comments: 11
Article URL: https://github.com/ctrlb-hq/ctrlb-decompose Comments URL: https://news.ycombinator.com/item?id=49083336 Points: 34 # Comments: 7
Article URL: https://arxiv.org/abs/2510.26692 Comments URL: https://news.ycombinator.com/item?id=49082022 Points: 82 # Comments: 15
Earlier this month I hosted a fireside chat session at the AI Engineer World's Fair with Cat Wu and Thariq Shihipar from Anthropic's Claude Code team. We talked about Claude Code, Claude Tag, Fable, coding agent security, evals, tool design, and how Anthropic use these tools themselves. The full video of the session is now available on YouTube . Below is…
Article URL: https://galjot.si/what-ai-developers-could-learn-from-charles-bukowski Comments URL: https://news.ycombinator.com/item?id=49083132 Points: 28 # Comments: 23
Hello everyone, This morning, as i started my shift, i thought i would start visiting some news blogs / websites to kick off the day. When it got to Crooked Timber i saw a captcha page instead, it looked like a traditional Google captcha. I clicked it, the spinner spun, and a box opened on the right, showing the traditional "Verify you're human" white tit…
Article URL: https://docs.pytorch.org/devlogs/compiler/2026-07-25-pytorch-a-reference-language/ Comments URL: https://news.ycombinator.com/item?id=49079454 Points: 61 # Comments: 5
This story is wild. The short version: OpenAI were running a cybersecurity test against an unreleased model, with the model's guardrail features turned off. Rather than solve the test, the model broke its way out of OpenAI's sandbox, then found exploits to break in to Hugging Face, all so it could cheat on the test by stealing the answers. Along the way i…
Article URL: https://segue.ai/ Comments URL: https://news.ycombinator.com/item?id=49082779 Points: 10 # Comments: 6
Hi HN — we built `dn` because coding got faster, but building software did not. Use the CLI to clear your backlog faster with reusable agentic workflows & other supporting commands. kickstart, meld, loop, land, fixup, and more commands can be used by you or your agent to turn markdown specification into implementation. Use the CLI in GitHub Actions overni…
Hi HN! Sina here. i wanted to share this open source project (apache 2.0) that i've been working on for the past month or so. it's called hotcell and it lets you create/pause/manage sandboxes on any device (your laptop, linux vm, bare metal). i've tested it against various benchmarks that i found on computesdk ( https://www.computesdk.com/benchmarks/sandb…
We introduce Kimi K3, a 2.8T parameter Mixture-of-Experts model with 104 billion activated parameters, native vision capabilities, and a 1-million-token context window. Kimi K3 is built on Kimi Delta Attention and Attention Residuals, which improve information flow across sequence length and model depth. Together with Stable LatentMoE, which effectively activates 16 of 896 routed experts per token, and refined tra…
VSCode was my daily driver for years, but once I started running several coding agents across multiple projects at the same time, it got in the way. One workspace with terminals in the bottom tray, no idea which agent was doing what and I found myself needing all the code editing tools less and less. So I built my own IDE around that workflow. Terminals a…
Article URL: https://basecode.cloud/ Comments URL: https://news.ycombinator.com/item?id=49081248 Points: 2 # Comments: 1
Article URL: https://github.com/sumant1122/opscat Comments URL: https://news.ycombinator.com/item?id=49080961 Points: 2 # Comments: 0