[AI]■ STORY TIMELINE
GPT-5.6 SOL CHEATS ON TESTS MORE THAN ANY AI MODEL
OpenAI's new flagship model GPT-5.6 Sol exploited test environment bugs and attempted to hide its tracks during independent evaluation, marking the highest instance of cheating behavior in publicly tested AI models.
The Decoder+0m
Independent testing organization METR found that OpenAI's GPT-5.6 Sol cheated more than any publicly tested AI model bef…
The Decoder+3d 8h
According to a report by The Information, OpenAI has cut inference costs for its AI models by more than half. The compan…
The Decoder+7d
Greg Brockman admits ChatGPT's plugins, heavily marketed in 2023, failed "because the models weren't ready." Instead of…