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 mckirk on Tuesday December 31, 2024 @12:30PM (#42560224)
This is actually something you probably want to avoid, if at all possible, because it makes it very hard to maintain insight into what the AIs are communicating among them. But that insight is crucial to stay informed about their progress in taking over the world, etc.
[ Parent | on HN ]
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 ]