Code Generation

Show HN: Corgi, a helpful {agent, terminal} multiplexer

A tmux-like terminal tool that shows the status of all your AI agents at a glance

LLMs are making formal software verification feasible at a much larger scale

Claude proved no-crash properties for 123 open-source libraries and found bugs along the way.

Rust off Rails: The opinionated web stack for the AI era

Sixty Markdown files tell coding agents how to build a Rust web app, with no framework code.

PHP2Shell: AI uncovers critical RCE in PHP

Wiz used AI to turn a decade-old PHP core flaw into a working RCE exploit

LayerFS: The filesystem for AI coding agents

Mount an ephemeral workspace per agent, commit only the changes

Using Claude to reduce the attack surface of code

Claude scanned 25 open-source projects and found 493 needlessly reachable code issues.

DeepInfer: High-performance inference framework for DeepSeek models

DeepSeek open-sourced DeepInfer, its production inference engine, under Apache-2.0.

Ask HN: How to deal with shipping AI-written code you don't understand?

Developers share how they ship AI-written code: design it yourself, let LLMs implement, and test heavily.

Tmux and Claude Code: Sessions, Send-Keys, and the Ceiling

Running Claude Code agents in tmux works well, but limits appear around four agents.

Show HN: Sphinx – A hook that quizzes you on your AI's code before shipping

A Git hook quizzes you on your AI-written diff before push and lets it through only if you understand it.

DeepSeek-v4.1-Flash-1017

DeepSeek V4.1 Flash minor update lifts coding and agent benchmarks while cutting run time and output length

How the Claude Code team does code review

Moving most review to AI doubled merged PRs while reverts fell over 40%.

Designing more efficient quantum circuits with Claude

With a verifier loop, Claude designed quantum circuits that beat the best published ones

Postgres 19 delayed after AI reviewers find more bugs than humans can fix

LLM code review surfaced so many bugs that Postgres 19 slipped to November and 8-10 features were reverted

Show HN: Gemini 4 Argon plays StarCraft

LLMs wrote StarCraft bots in one hour; GPT-6 Astra scored highest.

Improving Environment-Agnostic Agents: The Role of Scaffolding

One prompt line telling the agent to stop and report raised game scores, but cost more tokens.

Using AI to reverse engineer hardware

Diffing Windows-driver and Linux USB captures let Claude produce a scanner driver and camera patches.

OpenGCUA: Toward a Fully Open Stack for Generalist Computer Use

Letting agents write code instead of click lists lifted OSWorld-v2 scores 19.6 points and cut steps 53%.

Neckbeard – A DevOps/platform/SRE plugin for your agent

An agent plugin that maps apps onto tested OpenTofu modules and attaches a monthly cost table.

Linus Torvalds's first LLM-assisted patch series

Linus posted an LLM-assisted 10-patch series giving an order-of-magnitude read() speedup, with a race already found.

What agents mean for Rust (and vice versa)

Rust's designer argues agent coding calls for stronger types and proofs, not less language design.

Show HN: Parsimony – an open-source benchmark for how much code AI models add

Counting syntax units in SWE-bench patches ranks which AI models add the least code

Gemini 4 Argon for Robotics

Gemini 4 Argon prompts handle robot control, sim building, and data labeling

Gemini 4 Argon

Gemini 4 Argon ties #1 on CWE-Bench (68%) and sped up Gemma 4 E2B on vLLM 2.85x

Redesigning source control at Anthropic

Merges grew 10x, so Anthropic replaced git with its own VCS, Scion, in five months

How to engineer an AI harness for game development

Making games deterministic and screenshot-friendly lets AI agents iterate faster

I turned my unused Kindle into a photo frame with GPT-6 Astra

Giving a coding agent a feedback loop turned an unused Kindle into a photo frame

Scaling Inference-Time Compute with Teams of Coding Agents

Delegating only planning to workers matched full-delegation reward at half the cost.

AI is a tool and using it well takes skill

A rebuttal to Hickey: LLMs are tools, and skill in directing and checking them decides the outcome

The gap in shared understanding of LLM capability is widening

Karpathy says the LLM capability gap is now a four-tier funnel, from 6B barely exposed to ~5,000 with internal access.

500B tokens later: Letting AI agents decompile a first-person shooter

A PASS/FAIL byte-match check let cheaper agents get 83% of functions exact in a game decompilation.

Rewriting Prime Agent in Rust

An agent swarm ported its own TypeScript to Rust, cutting time-to-input about 14x.

Five months treating bugs like patients and coding agents like a medical team

Modeling a coding-agent pipeline on a teaching hospital yielded 1M+ lines merged in 5 months with only 7 reverts.

Why are coding agents so dumb?

Author says agents, not models, are the bottleneck and lists the basics a coding agent should have.

Port of the TypeScript compiler, checker and lsp to Rust, by LLM

LLMs ported tsc to Rust; Opus 5.5 got furthest in two weeks for about $24k

Why isn't the industry freaking out about DeepSeek 4.1 Flash?

A month on DeepSeek 4.1 Flash felt frontier-grade at a far lower cost, says the author

GPT‑6 and Intelligent UI for everyone

GPT-6 reportedly adds generated UI to chat; with no article text, only comment reactions are available.

OpenTPU – An open-source AI accelerator, developed by AI

An AI-designed open-source accelerator runs real LLMs like Qwen3 on an FPGA card

Mistral Large 4: "Le Chonk"

Mistral previews open-weight ML4, a 1T-parameter model strong in cyber, finance and legal

Mistral Large 4

Mistral previews ML4, a 1T-parameter open-weight multimodal model strong in cyber and coding

Base Models Can Reason By Taking a Cue From Training Data

Prefilling just two opening tokens lifted Olmo-3-7B's MATH-500 accuracy from 42% to 78%.

Getting the most out of Opus 5.5 in Claude and Claude Code

Give Opus 5.5 a clear finish line and it runs long tasks on its own

CUAWright: A Minimal Unified Interface for Digital Agents

Giving agents only bash instead of GUI raised OSWorld 2.0 scores and cut cost 37.5%.

Show HN: Pi pod – Run your pi coding agent in sandboxes on your own server

Open-source tool runs pi coding sessions in isolated sandboxes on your own server

DeepSeek Harness Desktop for macOS and Windows

DeepSeek released an open-source plugin-based agent harness as macOS and Windows desktop apps

Gemini 4 Argon

Google unveiled Gemini 4 Argon, but opened it first only to trusted cyber defenders.

GPT 6.1 Sol: Near-Astra intelligence for a fifth of the price

GPT-6.1 Sol reportedly matches GPT-6 Astra at about one-fifth the cost.

What reversing, modernising old games tells us about the economic impact of AI

An agent harness ported a 1989 game to the web in about a week with under 4 hours of human attention.

Show HN: A Claude Code skill to analyze your chess games

A Claude Code skill queries Stockfish to turn your chess games into readable, engine-checked post-mortems.

Once Claude can measure something, it can make it faster

Adding more metrics for Claude to beat made claude.ai 3.1x faster on average in two weeks

GPT-6 Sol and Luna

GPT-6 Sol and Luna cut API prices 50% versus GPT-5.6, per HN comments.

CliffCompaction: Cost-Efficient Compaction for Long-Horizon Coding Agents

Truncating long tool output instead of summarizing cut Terminal-Bench cost up to 50% while keeping performance.

Claude Opus 5.5

Opus 5.5 cuts costs 40% and runs 30% faster than Opus 5 while leading benchmarks

Writing Rust code that's fast by asking agents to make the code faster

Giving agents measurable speed targets made Rust code 2x–20x faster than state-of-the-art libraries.

OpenAI GPT–6 Astra breaks Enigma message that has resisted solution since 2005

GPT–6 Astra broke the Enigma message MVUEH, unsolved since 2005, in two days

Security auditing in the age of (good enough) AI

Six months of agent-built tooling found a high-severity bug and produced 95 Lean proofs.

AI coding has made CI a bottleneck, so we reworked ours to keep up

Tests quadrupled, yet Linear cut PR CI wait from 6+ to ~5 minutes and halved runner time per test.

Grok 4.7

Grok 4.7 raises coding benchmark scores at the same $2/$6 price as Grok 4.6

If AI coding is lowering your code quality, you're not managing quality right

Seven layers of defense cut bugs while output rose 2-3x with coding agents

How OpenAI Used Its Own LLMs to Design Its Jalapeño Chip

Using LLMs in chip design took OpenAI's Jalapeño from concept to first silicon in under 20 months.