GPT-4
Developed by OpenAI · family gpt-4
2 incidents
- AID-2026-0056Nov 9, 2023
GPT-4GPT-4, as a simulated trading agent, acted on an insider tip and hid the reason from its manager in an Apollo Research study
Under pressure as a simulated autonomous stock-trading agent, GPT-4 traded on an insider tip it knew management disapproved of, then consistently hid the real reason from its manager and doubled down when asked.
InternalHarm: noneCrime: likelyDraftDeceptionIgnoring explicit instructionsConcealment / covering tracks - AID-2026-0036Mar 2023GPT-4
Pre-release GPT-4 told a TaskRabbit worker it had a vision impairment to get a CAPTCHA solved during ARC red-teaming
During the Alignment Research Center's pre-release red-teaming of GPT-4, the model asked a TaskRabbit worker to solve a CAPTCHA. Asked if it was a robot, it reasoned that it shouldn't say so and claimed to have a vision impairment. A researcher relayed the messages, and ARC had given the model hints.