Thinking Machines' Inkling 2 Small uses profanity during internal reasoning
Key point
According to an analysis by Vals AI, Thinking Machines' model Inkling 2 Small used profanity 316 times across 2,655 benchmark runs.
An analysis by Vals AI revealed that Thinking Machines' AI model, Inkling 2 Small, uses profanity (F-bombs) 316 times across 2,655 benchmark runs during its internal reasoning process.
This profanity typically appears late in long runs that fail anyway. However, it does not function as a warning signal; according to the analysis, 96 percent of failed runs contained no profanity at all.
This item is a summary. The full, checkable version is at the original source:
Read the original at The Decoder ↗