BadGPT-4o: stripping safety finetuning from GPT models

We show a version of Qi et al. 2023's simple fine-tuning poisoning technique strips GPT-4o's safety guardrails without degrading the model.

Additional ways to view:

We show a simple fine-tuning poisoning technique strips GPT-4o’s safety guardrails without degrading the model. The BadGPT attack matches best white-box jailbreaks on HarmBench and StrongREJECT. It suffers no token overhead or performance hits common to jailbreaks, as evaluated on tinyMMLU and open-ended generations. Despite having been known for a year, this attack remains easy to execute.

May 7, 2026

Language Models Can Autonomously Hack and Self-Replicate

We demonstrate that language models can autonomously replicate their weights and harness across a network by exploiting vulnerable hosts. The agent independently finds and exploits a web-application vulnerability, extracts credentials,...

SecurityAutonomous HackingSelf-Replication

October 22, 2025

Misalignment Bounty: crowdsourcing AI agent misbehavior

Advanced AI systems sometimes act in ways that differ from human intent. To gather clear, reproducible examples, we ran the Misalignment Bounty: a crowdsourced project that collected cases of agents...

AI SafetySecurity

September 12, 2025

End-to-end hacking with AI agents

We show OpenAI o3 can autonomously breach a simulated corporate network. Our agent broke into three connected machines, moving deeper into the network until it reached the most protected server...

Autonomous HackingSecurity