HACKER NEWS

Write code like a human will maintain it: why AI-generated shortcuts teach future models bad patterns, and what the HN debate suggests for keeping quality up.

Apple sues OpenAI over alleged trade secret theft: what the complaint says about former employees Tang Tan and Chang Liu, the hardware angle, and HN reactions.

A solo developer built a 1,300-line C inference engine that runs the 744B GLM 5.2 model on consumer hardware by streaming routed experts from disk.

Ginger Bill argues that the best tools disappear during use - and that celebrating workarounds is a sign your tool has failed you.

GPT-5.6 Sol Ultra proof of the Cycle Double Cover Conjecture: what OpenAI claims, the prompt it used, and why mathematicians are still verifying the result.

Mitchell Hashimoto on building Ghostty in Zig: why he chose Zig over Rust, how the GPU-first terminal is architected, and what Hacker News made of it.

Scarf moves from Haskell to Python after 7 years: why LLM-driven development made compile times a bottleneck, how the migration worked, and the HN debate.

Tencent's Hy3 ships 295B parameters but activates only 21B per token, matching flagship performance at flash-tier pricing under Apache 2.0.

Does codebase pattern consistency drive AI output quality? The case that it makes rewrites economical, and why HN pushed back on maintainability and evidence.

Bun rewrote 535K lines of Zig to Rust in 11 days with Claude. What the port fixed, what it cost, and what HN thinks it means for LLM-assisted code migration.

GLM 5.2 UK VAT return benchmark: how the model handled 59 transactions with near-human bookkeeper accuracy, where it erred, and why HN focused on liability.

Grok 4.5 coding model from xAI, trained on Cursor data: $2/M input pricing, benchmarks near Opus 4.7, the CursorBench caveat, and the Hacker News reaction.

Meta Muse Spark 1.1 is Meta's first paid, closed-weights API model, with $1.25/M input tokens and 1M context. The pricing, benchmarks and HN debate.

pgrust, a Rust rewrite of PostgreSQL, passes all 46,000+ regression test queries. What it delivers, what it does not, and the HN debate on AI-assisted rewrites.

Cloudflare Meerkat is a QuePaxa-based consensus service with no leader elections or timeouts across 330+ data centers. Why not Raft, and what HN critiqued.

GitLost is a prompt injection flaw in GitHub Agentic Workflows that let attackers extract private repo contents via public issues. How the attack works.

An 82M parameter text-to-speech model that runs on CPU and produces high-quality speech across multiple languages - no cloud APIs or GPU required.

Mistral Robostral Navigate is an 8B robotics model that navigates with only a camera and natural language commands. How it works and what the benchmarks mean.

TypeScript 7.0 ships a Go rewrite of the compiler with 8-12x build speedups and faster editors on large codebases. Benchmarks, why Go, and what changes.

An obfuscated bash script on a Uniqlo x Akamai t-shirt, decoded: what the base64 payload does when run, and why HN argues over whether it was AI-generated.