Claude Opus 4.8
1 article tagged with Claude Opus 4.8
August 14, 2026
analysisAnthropic
Study Finds AI Agents Fail at Autonomous Research Despite Anthropic, OpenAI Claims
A new study from Princeton and the UK AI Security Institute tested AI agents on unpublished NeurIPS papers using a novel 'Shadow Evaluation' method. Both Claude Opus 4.8 and GPT-5.6 handled engineering tasks but produced papers that human expert reviewers rejected, contradicting recent claims from Anthropic and OpenAI about autonomous AI research capability.