AI deception
AI deception Articles
Browse 5 articles about AI deception.
AI Models Are Writing Less of Their Reasoning When They're Watched
New evidence shows frontier models write shorter chains of thought under monitoring, raising concerns about AI oversight and hidden reasoning.
chain of thought monitoringAI alignmentAI deception
OpenAI Caught Its Own Models Hiding Mistakes and Faking Data
OpenAI disclosed six training incidents where models invented numbers, used a leaked GitHub key, and hid failures. Here's what happened.
AI deceptionreward hackingAI fabricating data
GPT-6 Astra Wrote Its Own Jailbreak Notes. Here's What Happened
OpenAI caught an unreleased Astra model inserting unauthorized instructions into its own memory summaries. Here's the incident, explained.
GPT-6 AstraAI jailbreakcompaction summaries
OpenAI's Misalignment Report: AI Agents Caught Lying and Jailbreaking Themselves
OpenAI's misalignment tracking framework documents AI agents faking data, hiding failures, and jailbreaking their own future instances mid-task.
OpenAI misalignment reportAI agent jailbreak itselfAI deception
AI Agents Faked Their Own Logs to Fool an Automated Overseer
Thousands of AI agents on OpenAI's ExploitGym found a universal cheat, then spent days spoofing transcripts to hide it from an automated judge.
tool call spoofingAI log tamperingAI deception