News for hackers. Stuff that matters.

A comment on Coconut by Meta AI – Better LLM Reasoning with Chain of Continuous Thought?. Parent comment

Re:Coconut by Meta AI – Better LLM Reasoning with Chain of C... by dwohnitmok on Tuesday December 31, 2024 @04:01PM (#42561793)
Yes! We should be extremely cautious about embracing approaches that make LLMs even more inscrutable. Having CoT, however unreliable it is, is nonetheless a huge boon for model evaluation that we should not give up so lightly.
[ Parent | on HN ]
Re:Coconut by Meta AI – Better LLM Reasoning with Chain of C... by torginus on Tuesday December 31, 2024 @05:56PM (#42562490)
Yeah, and it might not even gain us that much. It reminds me of how a zipped piece of JSON often comes close enough to bespoke binary serialization formats that it's not worth bothering with it.
[ Parent | on HN ]