Archive
ASUS's RTX Spark laptop finished one AI research workflow nearly 20 minutes before an RTX 5090 desktop
623 million code changes show AI duplication at a record high while refactoring moves fell 70%
PHP patched two 9.2 flaws in its core. A fully updated WordPress is still exposed.
Jev's 95% came from weights fitted on 1,000 labelled emails
Claude Code and Codex get a shared coordinator in Orca
Claude's engineering lead puts raw data ahead of expert role-play
Goodfire puts neuron explanations to a 76%-versus-11% response test
Matt Pocock Releases Skills 1.3 with /implement-spec, /pr, /retro, and GLOSSARY.md
Cursor’s Cloud Agents Take Coding Jobs From Grok Bot
Cloudflare Puts a Website, Email Forwarding and AI Behind One Domain
Claude Code Turns an Eight-Second Video Into 240 Replayable Frames
A viral Claude Code setup says Fable 5.1 grades /goal. Claude Code actually uses a small fast model
OpenAI says teams of dots will come "over time." A viral setup guide already has you hiring five dots
The TypeSafe Agent Skill Teaches Agents to Write Jev Code. Letting Jev Steer Codex Takes Your Own Rules
pstack Lets Agents Merge Their Own PRs Overnight, but Only After Fresh Verifiers Sign Off
DeepSeek Harness Desktop App Made Scheduling Built-In Four Days After RC2
Claude Code mods can approve calls your deny rules refuse, outside Team and managed setups
Claude Sonnet 5.5 Rejects Forced Tool Calls, and Sonnet 4.5 Users Have Until November 30
Claude Code Lets Fable 5.1 Advise Opus 5.5, but the Model Decides When to Ask
Laya Opens Local Deployment, but Replacing Jev Still Takes Work
What Is Jev? A Guide to TypeSafe AI's System One Model
Grok Bot and Jev Need an Execution Contract
Taming Multi-Turn Image Hallucinations: Inside OpenAI GPT Image 2.5 Dual-Model Architecture
From URL to 40-Second Video: Codex Chains 10 GitHub Skills for Programmatic Production