← Back to context

Comment by sebastiangrill

4 hours ago

What tasks? Creating a extraordinarily mundane bomb?

No, it found a vulnerability in my code and refused to update a report I was working on with the information.

  • interesting.. Can you have a dumber agent do the work 5.5 refuses?

    • Once it refused, I couldn't get any of the models to continue. I tried Sonnet and it said the same "safety" check could not be bypassed.