Are these guys talking about search, like search search, like heursitc search, like GOFAI search?

Not sure what to make of all these complaints about reviewers and metareviewers being unreasonable and all that. People, we all know what game we are playing. #neurips Also, we have an accepted paper 🙃 stay tuned Lennert De Smet en.wikipedia.org/wiki/The_Myth_…

This Nobel prize is peak Ai hype and the most braindead decision I have seen, even when considering that they once gave the physiology prize to the guy who invented lobotomy.

haaa, forgot the link 🫠 arxiv.org/abs/2410.12389

🦋

1/n LLMs w/ T-CoT steps can solve reasoning problems in P/Poly. But they are not learning to reason - mimicking form, not logic. Are LRMs like DeepSeek R1 different? We formalize this in our paper: Have LLMs Learned to Reason? A Characterization via 3-SAT Phase Transition 🧵👇