Tootfinder

@…
Incidentally, just after you posted, author Greg Egan posted a conversation a different author had with an AI that is stunningly impressive until the end, which reveals that the AI text was thoroughly and fatally flawed in a horrible way, and it just lied.
It's long, but you could skim the beginning and then skim the end if you are time-limit…

LLMs exhibit "potemkin understanding"!
Hope the methodology here is better than the last LLM-hater arxiv paper that came through
Must read it more carefully...
https://mathstodon.xyz/@gregeganSF/114758840374128081

Greg Egan (@gregeganSF@mathstodon.xyz)
Attached: 1 image “Potemkin Understanding in Large Language Models” A detailed analysis of the incoherent application of concepts by LLMs, showing how benchmarks that reliably establish domain competence in humans can be passed by LLMs lacking similar competence. H/T @acowley@mastodon.social Link: https://arxiv.org/abs/2506.21521