HACKER NEWS

Gleam moved to Tangled, an ATProto-based code forge. What Tangled offers, what HN said about it, and what you gain or lose by leaving GitHub.

GPT-5.6 helped produce a Lean-verified proof closing a 1996 gap in derivative-free convex optimization. How the 10-page expert prompt worked, and what HN said.

A guide to setting up an isolated spare Mac that Claude Code can control remotely over SSH, Remote Control from your phone, and Tailscale.

SQLite in production lessons from Julia Evans: the ANALYZE fix that cut a query 100x, batching writes around the single writer, and backups that work.

Stack Overflow question volume is down 65% from its peak, with a sharp drop after ChatGPT. The graph, and the HN debate over whether AI killed the site.

TP-Link Kasa cameras leaked precise home GPS coordinates over unauthenticated UDP for years. How the flaw works, the disclosure timeline, and the second CVE.

AWS billing bug: a unit conversion error in S3 cost estimates sent developers alerts for billions and even trillions of dollars. What caused it and what to do.

How a 60-second auto-continue timer shipped to Claude Code without documentation, what it reveals about agent safety assumptions, and how to disable it.

Frame is an X11 server in 20,000 lines of assembly, built with Claude as a natural language compiler. It runs Firefox and GIMP on a third of Xorg's idle CPU.

Laura Summers of Pydantic articulates why LLM-assisted programming increases work intensity while eliminating the rewards that made coding satisfying.

LM Studio launches Bionic, a standalone agent harness for open models with local inference, voice input, and zero data retention cloud options.

Mozilla's State of Open Source AI report puts open models within 3.3% of closed ones, yet only 51% reach production. The deployment barriers explained.

Detecting LLM text with classical ML: how a TF-IDF and linear SVM detector reached about 85% accuracy without neural networks, and the HN false positive debate.

NotebookLM is now Gemini Notebook. What the rebrand changes, what stays the same for existing workflows, and what Hacker News developers are watching for.

Kimi K3 is Moonshot's 2.8T-parameter model with a 1M-token context and Delta Attention. Pricing, HN reactions and where it fits among frontier models.

Roc's Rust-to-Zig compiler rewrite took 487 days. What the memory safety numbers, 35ms incremental rebuilds and the HN reaction actually show.

AI voice fraud needs only three seconds of audio to clone a voice, and detection has failed. The defenses that work and what voice tech builders should change.

Gemma 4 26B on a 2013 Xeon with no GPU: how a sub-$300 box reached about 5 tokens/sec, the silent MoE bug behind the gibberish, and the upstream fix.

Days after getting caught uploading entire codebases to xAI servers, Grok Build is now open source on GitHub. The HN community isn't convinced it's enough.

A new American open-weights frontier model with multimodal capabilities, 1M token context, and competitive benchmarks. Here's what the HN community thinks.