Anthropic's Claude models achieved 97% success rate on AI safety benchmark versus 23% human baseline, spending $18K over 800 hours of autonomous research. (Read More)
Anthropic's AI Researchers Outperform Humans 4x on Alignment Task
1 month ago
28
Anthropic's Claude models achieved 97% success rate on AI safety benchmark versus 23% human baseline, spending $18K over 800 hours of autonomous research. (Read More)
Related
English (US)