by 1xdevloper on 4/10/23, 4:46 PM with 7 comments
by ianbicking on 4/10/23, 10:52 PM
I found the part on "reflection" was particularly interesting.
The cost of the simulation is also notable, going up to a thousand dollars for 3 days, running on GPT 3.5. That's very high from my experience doing this sort of thing, but not unimaginable when you do things in a loop, and if you are doing 25 queries on a clock tick. But should be very optimizable.
by 1xdevloper on 4/10/23, 4:46 PM
by alach11 on 4/10/23, 5:29 PM
by mdaniel on 4/11/23, 1:26 AM
by einsteinsapples on 4/10/23, 6:29 PM