I was on call for this run and got paged when the first incident happened. It was pretty surreal to watch the model unexpectedly find a way to access the internet from what was supposed to be a super secured environment for human.
Mixed feelings. One of those moments where capability and risk showed up at the same time.
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
Pretty impressive. I think I'll keep playing with this.
Prompt: "Read and follow its skills/baoyu-design/SKILL.md to design a home screen for a meditation app."
That prompt got me this:
Scoppr and Nook copied Mole. Researchers have linked both to malware that can steal passwords and personal data. Do not download or run them.
Neither is affiliated with me. Mole’s only official website is Please download it there.