Remix.run Logo
▲ saithound 6 hours ago

385x? Them's rookie numbers. Classical energies learn to reason 1000x faster than looped models. [1] Of course, all for a very generous definition of reasoning, that has almost nothing in common with the thing most people associate with the term nowadays. [2]

[1] https://arxiv.org/abs/2611.17309

[2] https://developers.openai.com/api/docs/guides/reasoning?api-...

▲yorwba 5 hours ago | parent | next [-]

The common definition of "reasoning" for all three is "performing a sequence of intermediate steps with multiple passes through the model before outputting an answer." The main difference is that the reasoning models in TFA and [1] are puzzle-solving models, not language models.

▲saithound 4 hours ago | parent [-]

Well, yes, that's the very generous definition of reasoning I was referring to, under which almost any iterative computation could count as reasoning.

▲ricardobeat 5 hours ago | parent | prev [-]

Did those two papers get published six days apart?