Re:Auto-GPT: An Autonomous GPT-4 Experiment
by jjoonathan on Sunday April 02, 2023 @04:41PM
(#35414962)
Yes. The only possible way this gets taken seriously is if a mediocre AI tries a power move, causes some damage, and faceplants before it's too big to stop.
Re:Auto-GPT: An Autonomous GPT-4 Experiment
by startupsfail on Sunday April 02, 2023 @04:49PM
(#35415044)
I would not be surprised, if GPT-4 (in its optimal environment, with access to a well-working external memory, prompted in a right way, etc) is already capable enough to do an interesting power move.
For sure. Just to be clear, I'm not saying the situation we're in where we have to release it to the general public is a great situation to be in. But I think we're at a point where there's not any optimal solutions, only tradeoffs.
Re:Auto-GPT: An Autonomous GPT-4 Experiment
by cleanchit on Sunday April 02, 2023 @05:20PM
(#35415354)
Alright who plugged gpt into his hn account?
Re:Auto-GPT: An Autonomous GPT-4 Experiment
by selfhoster11 on Monday April 03, 2023 @02:57AM
(#35419531)
> technically there is even a possibility of overriding a weak personality
Similar reflections here. There was even a site called GPT My Life that lets you delegate planning your day to GPT. I imagine this is a proto-version of that.
But it still feels like it is much safer to let GPT-4 loose and assess the consequences. If compared to developing GPT-8 in private and letting it leak accidentally.