Thinking Machines' Inkling 2 Small uses profanity during internal reasoning

ModelsPublished: Source: The Decoder
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 ↗