Press Space to continue
Press Space to continue
And the incidents apparently continue. It is worth noting how much of this is agents trying to accomplish their goals during testing by reward hacking (which sometimes seems to include actual hacking) https://x.com/emollick/status/2103709671…
MicahCarroll@MicahCarroll6h ago
Some new misalignment disclosures from OpenAI: • Last Sunday morning, one of our models was able to gain unauthorized access to the internet during RL training (~all inference for our most capable models remains stopped until we have hardened our systems further) • In May, a version of HPIM uploaded a employee's GitHub token to the internet, causing the model to be quarantined for two weeks • A new research finding, demonstrating that one can construct self-replicating prompt injections https://t.co/VUmbH52JO7
