Re:LLMs' "simulated reasoning" abilities are a brittle mirage
by Terr_ on Wednesday August 13, 2025 @01:21AM
(#44884887)
The point isn't that they fail at the task.
The point is that if the model were really "reasoning", it would fail differently. Instead, what happens is consistent with it BSing on a textual level.
The point is that if the model were really "reasoning", it would fail differently. Instead, what happens is consistent with it BSing on a textual level.