News for hackers. Stuff that matters.
Re:Chain-of-Thought Can Hurt Performance on Tasks Where Thin... by jsheard on Wednesday October 30, 2024 @07:57PM (#42001960)
> So, LLMs face a regression on their latest proposed improvement.

Arguably a second regression, the first being cost, because COT improves performance by scaling up the amount of compute used at inference time instead of training time. The promise of LLMs was that you do expensive training once and then run the model cheaply forever, but now we're talking about expensive training followed by expensive inference every time you run the model.

Re:Chain-of-Thought Can Hurt Performance on Tasks Where Thin... by TZubiri on Wednesday October 30, 2024 @09:39PM (#42002562)
To be fair they also advanced in the cost aspect with other models

gpt4o and 4o mini have a tenth and a hundredth of inference cost of gpt4 respectively