Re:OpenAI dropped the price of o3 by 80%
by anticensor on Tuesday June 10, 2025 @02:40PM
(#44239938)
-pro models appear to be a best-of-10 sampling of the original full size model
[ Parent
| on HN ]
how do you sample it behind the scenes?
usually best of X means you generate X outputs and you choose best result.
if you could do this automatically, it would be game changer as you could run top 5 best models in parallel and select best answer every time
but it's not practical because you are the bottleneck as you have to read all 5 solutions and compare them
Re:OpenAI dropped the price of o3 by 80%
by joshstrange on Tuesday June 10, 2025 @04:09PM
(#44240929)
I think the idea is they use another/same model to judge all the results and only return the best one to the user.
Re:OpenAI dropped the price of o3 by 80%
by anticensor on Wednesday June 11, 2025 @06:08AM
(#44245952)
I think the idea is they just feed each to the RLHF reward model used to train the model and return the most rewarded answer.
Re:OpenAI dropped the price of o3 by 80%
by anticensor on Tuesday June 10, 2025 @05:25PM
(#44241618)
> if you could do this automatically, it would be game changer as you could run top 5 best models in parallel and select best answer every time
remember they have access to the RLHF reward model, against which they can evaluate all N outputs and have the most "rewarded" answer picked and sent