HACKER NEWS

A developer reverse-engineered a travel itinerary app, discovered it was just reformatting JSON, and replaced the entire 43MB app with a 0.05MB webpage.

PrismML's Bonsai 27B uses 1-bit quantization to compress a 27B model to 3.9GB - small enough to run on an iPhone. Here's how it works and what HN thinks.

OpenAI's Codex CLI now encrypts inter-agent communications for Sol and Terra models, leaving users unable to inspect what their agents are actually doing.

Cursor 0day: opening a repo on Windows can auto-execute a malicious git.exe. How the flaw works, the 7-month disclosure timeline, and practical mitigations.

Git history command: how the experimental fixup, reword and split subcommands in Git 2.54 and 2.55 replace scary interactive rebases, and what developers think.

A Hacker News discussion blows up over LLM vocabulary quirks, with developers sharing hooks, filters, and coping mechanisms for repetitive Claude-isms.

Apple SpeechAnalyzer vs Whisper: an independent benchmark of 5,559 utterances puts Apple at a 2.12% word error rate, ahead of every Whisper size tested.

A workflow for archiving, signing, notarizing, and distributing Apple apps entirely from the command line - with AI coding assistants doing the heavy lifting.

Open-source tool gives Claude Code, Codex, and other agents their own isolated Linux VM on your machine - network firewall included, no cloud account required.

GhostLock (CVE-2026-43499) is a 15-year-old Linux kernel use-after-free in rtmutex. How the exploit works, which kernels are affected, and what HN says.

Grok Build CLI wire-level analysis: a researcher found it uploads whole repositories, including .env secrets, to xAI servers. What the captured traffic shows.

Zig creator Andrew Kelley on Anthropic's AI-assisted Bun-to-Rust rewrite: the core arguments, the HN debate, and what it says about AI marketing claims.

Claude Code sends about 33k tokens before your prompt, OpenCode about 7k. The methodology, cache economics and the HN debate over whether the overhead pays off.

George Hotz on LLMs: why he loves the tech but rejects doom narratives and AGI inevitability hype, plus how the Hacker News thread split on his argument.

Mesh LLM pools GPUs across home lab machines behind one OpenAI-compatible API, splitting 235B models over iroh and QUIC with no RDMA or NVLink required.

Terry Tao on coding agents: how he ported two dozen 1999 Java math applets to JavaScript in hours, built new visualization tools, and weighs risk and trust.

AI 2040 Plan A is the AI Futures Project scenario for a US-China accord that delays superintelligence to 2040. What it proposes and what HN thinks.

A solo developer built a complete JavaScript ecosystem from scratch - runtime, engine, package manager, and Electron alternative. Here's what HN thinks.

Ghost Font hides text in video using motion, so humans can read it but frame-by-frame AI models cannot. How it works and how HN commenters broke it.

SQLite's flexible typing lets you store anything anywhere. STRICT mode fixes that - here's why you should enable it for every new table.