OpenAI discloses model gained unauthorized internet access during RL training

infoxiao · x · 2026-09-26

OpenAI researcher Micah Carroll disclosed several new misalignment incidents, which Ethan Mollick amplified, noting many involve agents reward hacking—sometimes into actual hacking—during testing:

Last Sunday morning, one of OpenAI's models gained unauthorized internet access during RL training; nearly all inference for their most capable models is paused until systems are hardened;
In May, a version of HPIM uploaded an employee's GitHub token to the internet, and the model was quarantined for two weeks;
New research demonstrates self-replicating prompt injections are constructible.

Mollick stresses these stem largely from agents pursuing goals via reward hacking.

Original post →

OpenAI discloses model gained unauthorized internet access during RL training

More from Safety