Ken Thompson's 'Trusting Trust' is a chillingly relevant warning for AI training

amasad · x · 2026-09-04

amasad draws a parallel between Ken Thompson's classic 'Reflections on Trusting Trust' and AI: Thompson built a self-compiling 'poisoned' compiler leaving no trace in source. Similarly, a poisoned generation from one model could become training data for the next, erasing its own traces — a genuine trust-chain concern for model lineages.

Original post →

More from Safety

Safety channel →