News for hackers. Stuff that matters.
Re:AI Report #4: AutoGPT And Open-source lags behind Part 2 by joshuanapoli on Sunday June 04, 2023 @03:32PM (#36188739)
In my experience, a GPT 3.5 or 4 agent has trouble accomplishing anything if you make too many APIs available. Using a completion to narrow down the list of options makes the entire exchange very slow. There is also a compounding chance of failure with multi-stage strategies; the “agent” may get stuck responding in the “wrong” way and burn up even more time with error recovery.

There are no comments on this comment yet.