|
|
|
|
|
|
by unglaublich
30 days ago
|
|
|
> Model refusals [..] That even their model aimed at security research tries to be a pedantic better-than-thou annoys me much. I build an agentic loop framework at work, and I need the model to test some boundaries and error-mechanisms, but Opus keeps whining that it's not ready to do these "bad" things and tells me to do it myself instead. Makes me roll my eyes... |
|
|