Can you tell AI from human-authored code and should you even care?
1 points, 0 comments on Hacker News
#code
Page 3 of 7 — 152 headlines
Meta launches Muse Code AI coding agent for macOS and Linux
Meta is entering the AI coding-agent race with Muse Code, a new terminal-based tool now available in beta for macOS and Linux.
Meta releases Muse Code coding agent in beta
Developing story — details emerging. Check the source link for the latest updates.
Muse Code and Muse Spark 1.2
20 points, 10 comments on Hacker News
Releasing Muse Code in beta today, and Muse Spark 1.2
3 points, 0 comments on Hacker News
The Framework Tax Is a Product Decision
A few years ago, the default test automation decision was mostly technical. Do we use Selenium? Which language?
Show HN: Ocean – All your team's agent sessions in one place
I spend a lot of time in Claude Code and Codex with my friend. We kept losing the context behind changes because every agent session lived on one person's laptop, and by the time code made it into a PR, all the reasoning was gone. We tried commits, PRs, and docs, but they only really capture th...
Show HN: What's Your AI Debt Score? Roast My Code – No AI, Just Regex
Paste your code, get an AI Debt Score (0-100), and get roasted for your sins. 118 regex patterns, 8 languages, zero AI involved — everything runs client-side, your code never leaves your browser. Curious what score you get.
Vibe-Coding Gone Wrong: Debugging AI-Generated Code
2 points, 0 comments on Hacker News
Stop Your AI Coding CLI From Wasting Tokens on "Hi" and "Thanks"
In this blog post, we will see how a small Python script called Pleasantries can stop your AI coding CLI from burning a full model call every time you type "hi", "ok", or "thank you". I built this after noticing how often my own prompts to Claude Code and Qwen Code started with a greeting out of...
From the Lab Bench to the Codebase: What Scientific Research Taught Me About Debugging
For over five years, my "bugs" weren't in code. They were in DNA sequencing runs that came back with unreadable peaks, PCR reactions that refused to amplify, and antioxidant assays that gave inconsistent results across replicates. I have a background in Biotechnology and a Master's in Chemical ...
Use DraftKings promo code to get $150 bonus bets by targeting Guardians-Mets, Royals-Twins, MLB on Wednesday
DraftKings offers $150 in bonus bets after your first $5 wager for MLB betting on Wednesday
Curie – ship Claude Code agents to Kubernetes with Git push
3 points, 0 comments on Hacker News
Use AI to make code better
1 points, 0 comments on Hacker News
⚠️ Shai-Hulud opens your IDE: the npm worm that beats --ignore-scripts
I cleaned the infected packages. I deleted node_modules . I ran npm ci --ignore-scripts .
Show HN: Arxid – keyed, non-enumerable ID obfuscation
I kept reaching for Hashids/Sqids to keep sequential IDs out of URLs, but they don't use a real key — the alphabet is shuffled by a salt, and the Sqids FAQ says outright "there is no encryption of any kind. " arxid is a keyed reversible permutation instead: a balanced Feistel network with an ARX ...
Use BetMGM bonus code CBSSPORTS to get $1,500 in bonus bets for Yankees-Cardinals, MLB betting on Wednesday
Use the latest MGM promo code CBSSPORTS to get $1,500 in bonus bets if your first bet loses for MLB betting on Wednesday
Sober: Local-first code reviewer for agentic PR (deterministic and model review)
1 points, 1 comments on Hacker News
Show HN: Code Factory – Create a reviewable MVP in minutes, with receipts
1 points, 0 comments on Hacker News
Show HN: 3D models, but they're 100% code
5 points, 4 comments on Hacker News
Measure your own coding habits before you believe anyone else's numbers
Part of "AI, engineering and what survives production", a series on the parts of building with AI that hold up once real traffic hits them. There is a claim going round that you have probably absorbed by now: AI-assisted development is making codebases worse. Refactoring is down, duplication is...
Claude Code Subagents: Setup, Config, and When to Use Them
Most Claude Code sessions get slow and cluttered for the same reason: every exploratory grep, every log dump, and every "let me check one more file" stays in the main conversation forever. Subagents exist to fix exactly that problem. They are one of the agent primitives built into Claude Code f...
Show HN: GuidedReview, a Chrome extension that helps review AI generated PRs
Every company I see has an automated code review agent set up in their repository. It doesn't solve the code review problem. The automated review agents cannot be trusted the same way coding agents cannot be trusted.
I built a short-code marketplace with zero npm dependencies (Node.js 22, no framework)
I've been going back and forth on whether to share this — it's a pretty niche idea, and I wasn't sure if it's clever or just weird. But here's the technical side of it, which I figure this crowd might actually appreciate regardless. What I built: claimo.