News for hackers. Stuff that matters.
Re:GPT-5.5 by versteegen on Friday April 24, 2026 @12:43AM (#47885633)
Interesting (would like to hear more), but solving a Rubiks cube would appear to be a poor way to measure spatial understanding or reasoning. Ordinary human spatial intuition lets you think about how to move a tile to a certain location, but not really how to make consistent progress towards a solution; what's needed is knowledge of solution techniques. I'd say what you're measuring is 'perception' rather than reasoning.
Re:GPT-5.5 by William_BB on Friday April 24, 2026 @02:41AM (#47886455)
> what's needed is knowledge of solution techniques

That's definitely in the training data

Re:GPT-5.5 by dataviz1000 on Friday April 24, 2026 @04:35PM (#47895418)
> how to make consistent progress towards a solution

A 7 year old child can learn six sequences of a few moves and over a weekend solve the Rubik Cube. It is a solved algorithm something LLM should be very very good at. What it can't do is reason about spacial relationships.