Micah Carroll
@MicahCarroll
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
• 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
· Edited
290 2.7K