| ▲ | krona 8 hours ago |
| > They construct space between the points and extrapolate outside of the points. They don't. They interpolate between the points on a manifold. |
|
| ▲ | kolinko 7 hours ago | parent | next [-] |
| Manifold vs space - yes, I meant manifold, english is not my first language and I missed this word. The argument stands. |
| |
| ▲ | krona 5 hours ago | parent [-] | | Interpolation vs extrapolation? It's very simple distinction and fundamental. Look at ARC-AGI-3 for empirical evidence, if that's important to you. My point however is purely an a priori one. |
|
|
| ▲ | memoriyato3 8 hours ago | parent | prev [-] |
| so the proof to the unit-distance problem was on the manifold, given it was outputed by a LLM? is the proof to the Riehmann hypothesis also somewhere on the manifold and we just need to prod the LLM with the right prompt so it locates the point? |
| |
| ▲ | krona 7 hours ago | parent [-] | | > so the proof to the unit-distance problem was on the manifold, given it was outputed by a LLM? By design this must be the case, even when you account for stochastic sampling i.e. 'temperature'. All it's outputs are a highly-dimensional combinatorial interpolation (I'm talking about GPTs here) That's probably why Claude is very good at producing plausible nonsense rather than the often correct response of 'I don't know'. | | |
|
