UK's AI Security Institute finds standard benchmarks systematically underestimate what AI agents can actually do

In a study covering seven benchmarks, the UK's AI Security Institute shows that standard AI evaluations systematically underestimate agent capabilities by capping the compute budget. On software engineering tasks, success rates jumped about 25 percent when the token budget was…

To respect copyright, we link to the source rather than republishing the full text. Read the complete article on The Decoder.