Efficient Reasoning with Hidden Thinking · HackerPapers discussions

Efficient Reasoning with Hidden Thinking — mentioned by easeout

Wed, 05 Feb 2025 15:37:30 GMT

Here's a paper your idea reminds me of. https://arxiv.org/abs/2501.19201 It's also so not far from Meta's large concept model idea.

Paper and discussion history. A mention is not an endorsement.

Efficient Reasoning with Hidden Thinking — mentioned by WhitneyLand

Tue, 04 Feb 2025 00:46:38 GMT

Examples go back 50 years, across many of the disciplines you’ve mentioned, but to throw out one that’s recent, on topic, and highly cited, there’s: Chain-of-Thought Prompting Elicits Reasoning in Large Language Models https://arxiv.org/pdf/2501.19201 It effectively treats “reasoning” as the ability to generate intermediate steps leading to a correct conclusion. Now, is this valid reasoning? Well, depends on the claim and the definition of reasoning. When someone just says AI can’t reason, I could argue for or against that depending on the specifics. It’s not enough to just say yes or no.

Paper and discussion history. A mention is not an endorsement.

Efficient Reasoning with Hidden Thinking — HN submission

Mon, 03 Feb 2025 16:06:48 GMT

Efficient Reasoning with Hidden Thinking

172 points; 43 discussion replies on HN. Paper and source history. A submission is not an endorsement.