Vals AI study: Thinking Machines' Inkling 2 Small swears 316 times in benchmark tests
Vals AI researchers analyzed the thinking logs of Thinking Machines' Inkling 2 Small across 13 benchmarks and 2,655 runs, discovering that 50 runs contained profanity. "fuck" Of these, 241 came from two runaway executions.
Return to original text
A short introduction is retained here; the full text from the source website is not reposted. For specific wording and subsequent updates, please refer to the original article.
Open AIHOT original