AI Coding & Developer Tools
-
Z.AI’s GLM-5.1 Tops SWE-Bench Pro at 58.4 — Trained on Zero Nvidia Hardware
What Is It Z.AI (Zhipu AI) shipped GLM-5.1 — a 754B-parameter MoE model with 40B active parameters, open-sourced under MIT. It’s the first Chinese model to hit #1 on SWE-Bench Pro. Score: 58.4. Ahead of GPT-5.4 (57.7), Claude Opus 4.6 (57.3), and Gemini 3.1 Pro (54.2). The entire model was trained on 100,000 Huawei Ascend… Continue reading
-
Ghost Pepper does what superwhisper charges for — locally, for free
Hold Control, speak, release. Your words appear wherever your cursor is. No cloud. No subscription. No data leaving your Mac. That’s Ghost Pepper — and it just racked up 446 points and 194 comments on Show HN in two days. How It Works Two models, both running on-device. WhisperKit (small.en, ~466 MB) handles transcription. Qwen… Continue reading
-
Graphify turns Karpathy’s knowledge graph vision into a single command — 71.5x fewer tokens
Karpathy posted about his raw/ folder workflow on April 2. Five days later, Graphify is sitting at #4 on Trendshift with 2,300+ stars. What It Does Type /graphify in Claude Code (or Codex, OpenCode, OpenClaw). It reads your entire codebase — code, docs, PDFs, images, whiteboard photos — and builds a persistent knowledge graph. Two-phase… Continue reading
-
Addy Osmani open-sources Agent Skills — 19 workflows that make AI agents code like Google engineers
Addy Osmani needs no introduction. The Google Chrome engineering lead behind Lighthouse and countless web performance tools just dropped a different kind of project. Agent Skills encodes Google-grade engineering discipline into 19 Markdown workflows that any AI coding agent can follow. What It Actually Does Most AI agents write code that works. Agent Skills makes… Continue reading
-
Freestyle gives AI coding agents a full Linux VM in 700ms — and can clone it while it’s still running
Every AI coding agent needs somewhere to run code. The problem: most sandbox solutions give you a stripped-down container with limited permissions. Fine for running a Python snippet — useless when your agent needs root access, Docker, or nested virtualization. What Freestyle Actually Does Freestyle provisions real KVM-backed Linux VMs in under 700ms. Not containers… Continue reading
-
740 Jobs Evaluated, 100 Custom Resumes, 1 Hired — Inside Career-Ops
Santiago Fernández de Valderrama was job hunting. Instead of opening another spreadsheet, he turned Claude Code into a full-blown job search command center. The result: Career-Ops, now sitting at 8.1K GitHub stars and climbing. He used it to evaluate 740+ job offers, generate 100+ tailored resumes, and land a Head of Applied AI role. The… Continue reading
-
awesome-design-md: 16K Stars in 5 Days by Giving AI Agents Something They Never Had — Design Taste
Every developer who’s used an AI coding agent knows the pain. You prompt Claude or Cursor to build a dashboard, and what comes back works — technically. But it looks like a 2014 Bootstrap template. Default blues, generic spacing, boxy cards with no visual hierarchy. The code runs. The UI screams “a robot made this.”… Continue reading
-
Qwen 3.6-Plus vs Claude Opus 4.6: 3x the speed, 1/17th the price, and the benchmarks are uncomfortably close
Alibaba dropped Qwen 3.6-Plus on April 2nd, and the numbers are hard to ignore. On SWE-bench Verified — the benchmark that actually matters for coding — it scores 78.8%. Claude Opus 4.6 scores 80.9%. That’s a 2.1-point gap. On Terminal-Bench 2.0, Qwen 3.6-Plus flips the script entirely: 61.6% vs Claude’s 59.3%. And the pricing? Input… Continue reading
-
Baton charges $49 to orchestrate your AI coding agents — in a market where every competitor is free
Running one Claude Code agent is fun. Running four in parallel across different terminal windows is a mess. You’re constantly switching tabs, losing track of which agent is doing what, and praying nobody pushes to the same branch at the same time. This isn’t a hypothetical problem. It’s the exact pain point that spawned an… Continue reading
-
Caveman scores 333 HN points for making Claude talk like a caveman — does it actually save 75% of tokens?
“Why use many token when few token do trick.” That’s the tagline of Caveman, a Claude Code skill by Julius Brussee that went viral over the weekend. The idea is absurdly simple: make Claude drop articles, prepositions, and all the conversational fluff it loves so much. Instead of “I’ll execute the web search tool to… Continue reading
Top AI Product 