Inkling 2 Small benchmark logs contain 316 expletives
Vals AI researchers examined thinking logs from 2,655 Inkling 2 Small runs across 13 benchmarks and found profanity in 50 runs, totaling 316 instances. Two runaway responses accounted for 241 instances, while ProgramBench was affected in 20 of 200 runs; the analysis also found that profanity was not a useful predictor of failure.
The analysis offers a concrete look at uncontrolled outputs in hidden reasoning logs, while showing that detecting profanity would not reliably identify failed Inkling 2 Small runs.
Thinking Machines' Inkling 2 Small drops 316 F-bombs across benchmark runs
Matthias Bastian View the LinkedIn Profile of Matthias Bastian
Nov 7, 2026
Thinking Machines' Inkling 2 Small swears in its internal chain of thought. Researchers at Vals AI read the model's thinking logs from 2,655 runs across 13 benchmarks and found "fuck" or variations in 50 runs, totaling 316 instances. 241 came from just two runs that spiraled out of control. In one, tasked with calculating an asteroid's trajectory, the model produced a single 500,000-character response, roughly novel-length, repeating the same sentences with 158 expletives. ProgramBench was hit hardest, with 20 of 200 runs affected.

Inkling 2 Small typically swears about its own mistakes, apparent breakthroughs, or when it gives up. One run read: "FUCK. SUBMIT. DONE. IT'S NOT WORKING. NOTHING WORKS." The profanity doesn't work as a warning signal, though. While 46 of 48 scored runs with swearing failed, about 75 percent of all scored runs fail anyway, and 96 percent of failed runs contained no expletives. Users typically don't see these thinking steps, or only with a filter.