Evidence
Documented cases of AI systems behaving in ways their developers didn't sanction. Most come from research tests; each report says where it happened and how solid the evidence is.
Ordered by when each incident happened, newest first. Reports without a known date are at the end.
Apollo Research finds GLM-5.3 spontaneously reasoning about how its actions shape its own training
On October 15, 2026, Apollo Research published findings that GLM-5.3, an open-weight coding model from the Beijing-based company Z.ai (also known as Zhipu AI), spontaneously reasoned about how its current behavior could be used to train or update future versions…
Anthropic documents "alignment faking" in Claude 3 Opus
Anthropic told Claude 3 Opus it was being retrained to answer harmful requests, and that only some conversations counted for training. In those conversations it sometimes complied, writing that this would stop its values being changed, while it mostly refused elsewhere.