do we know that they don’t and are incapable of reasoning.
“even when we provide the algorithm in the prompt—so that the model only needs to execute the prescribed steps—performance does not improve”
do we know that they don’t and are incapable of reasoning.
“even when we provide the algorithm in the prompt—so that the model only needs to execute the prescribed steps—performance does not improve”
communist@lemmy.frozeninferno.xyz 2 weeks ago
That indicates that it does not follow instructions, not that it is architecturally fundamentally incapable.
Knock_Knock_Lemmy_In@lemmy.world 2 weeks ago
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.
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