Welp, it's now blocking me from doing extraordinarily mundane tasks because of "safety". I've been an Opus fan for a long time, but this instantly made me cancel my subscription and move to OpenAI (which I also assume will screw me soon enough). Chinese models are almost there for my needs, and I can't wait to switch to them and never look back.

▲

sebastiangrill 4 hours ago | parent [-]

What tasks? Creating a extraordinarily mundane bomb?

▲

slowin 4 hours ago | parent [-]

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

▲

yehosef an hour ago | parent [-]

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

	▲	slowin an hour ago \| parent [-]
		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.