A reported demonstration shows GPT-5.5 reproducing a claimed solution to the Erdős unit distance problem with a diagram titled “Impressive Reasoning Abilities of LLMs” that flags prompter assistance
Researchers note GPT-5.5 Pro matches results via parallel strategies and extra test-time compute.
#92(((ل()(ل() 'yoav))))👾@YOAVGOthis is a clear demonstration of:
it still shows impressive abilities, but diff one than those advertised for the "internal model"
(((ل()(ل() 'yoav))))👾@yoavgothis is a clear demonstration of:
@littmath it might get distracted. and it requires scaffolding, which the current model supposedly did without. and it should know when to continue. these are all failure points in my experience. (also, "combine 1, 2, 5" is kinda big imo)
Daniel Litt@littmath@yoavgo I think I broadly disagree; I think the hints are minimal enough that I would expect 5.5 Pro to get there with good scaffolding and lots of test-time compute, just by trying the strategies it listed in parallel.
@yoavgo Very clever Hans of these models!
(((ل()(ل() 'yoav))))👾@yoavgothis is a clear demonstration of:
I have been digging into the openai erdos result tonight and it's the first time in a while that I really got goosebumps from science and im not even that much into math.
But the problem is so simple and easy to understand, and the model's (dis)proof is only 2 pages.
#1644Konstantin Mishchenko@KONSTMISHAt first it felt like Perelman emerging from years of seclusion with a proof to the Poincaré conjecture. But the fact that we didn't need a model to do 125 pages of thinking somehow made the achievement seem a lot less impressive to me.
Daniel Litt@littmathPretty interesting -- ChatGPT 5.5 Pro, with pretty minimal human guidance (and apparently without web search), also finds the counterexample to unit distance.