Post

Conversation

Noah Smith 🐇
@Noahpinion
Click to Subscribe to Noahpinion
AI wins!!
Quote
Rohan Paul
@rohanpaul_ai
A follow-up study on Apple's "Illusion of Thinking" Paper is published now. Shows the same models succeed once the format lets them give compressed answers, proving the earlier collapse was a measurement artifact. Token limits, not logic, froze the models. Collapse vanished x.com/rohanpaul_ai/s…
Show more
Image
22.7K
Views
David Watson 🥑
Post your reply

Recreational Tweeting
@Thx4Reading
At least some of the criticisms of the original paper seem to be legitimate, but changing the test to whether reasoning models can output code that was in their training data is not addressing the same question.
109
R . R .
@ckrlft
I mean, everybody knew that the paper was apple being butthurt that they are not competitive at all in the field.
248