arXiv:2403.04121cs.AI
While humans sometimes do show the capability of correcting their own erroneous guesses with self-critiquing, there seems to be no basis for that assumption in the case of LLMs.
Linked by 2 identifiable commenters in 2 comments across 2 threads, from Mar 2024 to Jan 2025. Found in 5 HN submissions from Mar 2024 to Apr 2024. Open submission discussions.
>> With our advances in long-term reasoning and planning, Devin can plan and execute complex engineering tasks requiring thousands of decisions. They'd better have really advanced reasoning and planning capabilities way beyond everything that anyone else knows how to do with…
Connected through shared HN threads, not inferred similarity or a recommendation.
Proof? :) where has proof ever been found in truth? It's not proof, but there is some good evidence out there. Here are two interesting papers I found informative. https://arxiv.org/html/2403.04121v2 https://arxiv.org/html/2411.12580v1
sgt101View on HNParent context