AI IntelligenceAug 15, 2026AI Intelligence
Article
A study using Claude Opus 4.8 and GPT-5.6 Sol found that AI agents given six days and $3,000 in API credits failed to produce...
Independent research, contradicting claims by Anthropic and OpenAI. The findings challenge the notion that autonomous AI research is within reach.
Data Cube AI EditorialSource: The Decoder
01
Source Brief
A study using Claude Opus 4.8 and GPT-5.6 Sol found that AI agents given six days and $3,000 in API credits failed to produce independent research, contradicting claims by Anthropic and OpenAI. The findings challenge the notion that autonomous AI research is within reach.
02