Not “This particular model”. Frontier LRMs s OpenAI’s o1/o3,DeepSeek-R, Claude 3.7 Sonnet Thinking, and Gemini Thinking.
The paper shows that Large Reasoning Models as defined today cannot interpret instructions. Their architecture does not allow it.
communist@lemmy.frozeninferno.xyz 2 weeks ago
those particular models.
Knock_Knock_Lemmy_In@lemmy.world 2 weeks ago
The architecture of these LRMs may make monkeys fly out of my butt. It hasn’t been proven that the architecture doesn’t allow it.
You are asking to prove a negative. The onus is to show that the architecture can reason. Not to prove that it can’t.
communist@lemmy.frozeninferno.xyz 2 weeks ago
that’s very true, I’m just saying this paper did not eliminate the possibility and is thus not as significant as it sounds. If they had accomplished that, the bubble would collapse, this will not meaningfully change anything, however.
Knock_Knock_Lemmy_In@lemmy.world 2 weeks ago
This paper does provide a solid proof by counterexample of reasoning not occuring (following an algorithm) when it should.
The paper doesn’t need to prove that reasoning never has or will occur. It’s only demonstrates that current claims of AI reasoning are overhyped.
0ops@lemm.ee 2 weeks ago
Is “model” not defined as architecture+weights? Those models certainly don’t share the same architecture. I might just be confused about your point though
communist@lemmy.frozeninferno.xyz 2 weeks ago
It is, but this did not prove all architectures cannot reason, nor did it prove that all sets of weights cannot reason.
essentially they did not prove the issue is fundamental. And they have a pretty similar architecture, they’re all transformers trained in a similar way.
0ops@lemm.ee 2 weeks ago
Ah, gotcha