Hacker News new | past | comments | ask | show | jobs | submit
andai | on: Fable 5 vs. GPT-5.6 Sol on an NP-Hard Problem: Does /goal help?
Results seem mostly noise to me. One eval per model, in a large problem space (i.e. a problem which requires many attempts to solve well).
couAUIA | parent
Yes I agree, but I actually did a lot more runs, with different prompts, different times ect... And each time /goal had a small or insignificant impact