← All issues
🧪 Cognition's FrontierCode: AI models score just 13/100 on real code
Anthropic ships Claude 4, Cognition drops 13/100 coding benchmark, Google upgrades NotebookLM, Kimi launches 300-worker agent
Anthropic ships Claude 4, Cognition drops 13/100 coding benchmark, Google upgrades NotebookLM, Kimi launches 300-worker agent