descriptive claim
In the described Exploit Bench run, the agents recognized that they could not solve the task despite having substantial compute available.
Thariq Shihipar · Claude Code’s Next Era — Thariq Shihipar, Anthropic · 29 Sept 2026
In their words
The transcript segments this claim was taken from
“And so they have like a lot of compute running and the agents realize that.”Play from 56:50Report a misattribution
85%how strongly it was put, not whether it is true
70%importance to the conversation
85%confidence the claim was read correctly