RESEARCH Meta Ends Its ‘Tokenmaxxing’ Push and Steers Staff to Its New Hatch AI Agent 8/10 2 min read 2 months ago
RESEARCH Princeton and UC San Diego Study Explains When ‘Skills’ Help AI Agents — and When They Backfire 8/10 3 min read 3 months ago
ANALYSIS Google’s Gemini API Managed Agents Add 3.6 Flash Default and Security Hooks 7/10 2 min read 4 months ago
RESEARCH OpenAI Field Report: AI Agents Shift Scientists From Coding to Verification 8/10 2 min read 4 months ago
ANALYSIS ‘Context Bombing’: Defenders Turn Prompt Injection Against AI Hacking Agents 7/10 3 min read 4 months ago
FUNDING Survey: Half of Enterprises Shipped an AI Agent That Passed Evals, Then Failed 8/10 2 min read 4 months ago
RESEARCH Code Is How AI Agents Think and Act, Meta-Stanford-UIUC Review Argues 8/10 3 min read 6 months ago
REGULATION Inside the AI-Agent Boom: From Claude Code Anonymous to 366K-Star Repos 8/10 3 min read 6 months ago
GUIDES Hugging Face Glossary: ‘Harness’ vs ‘Scaffold’ vs ‘Agent’ Defined 7/10 3 min read 6 months ago
