"phd-level reasoning"

https://lemmy.world/post/40418364

The web search poisoned it. ChatGPT with web search off gets it. As well as basically every other LLM.

Its response:

This is a trick riddle built on the classic wolf–goat–cabbage problem.

Key twists:

  • The goat is dressed up as the farmer → there is no separate farmer to manage conflicts.
  • The goat is allergic to cabbage → it won’t eat the cabbage, so that danger is removed.
  • The goat is “wolfing down other vegetables” → those vegetables are already eaten before the crossing.
  • After that, only the goat and the cabbage remain, and they are safe together.

So there are no constraints left to manage.

✅ Minimum number of trips needed: 1

The goat simply crosses the river once.

I mean, this is just one of half a dozen experiments I conducted (replicating just a few of the thousands that actual scientists do), but the point stands: what PhD (again, that was Sam Qltman’sclaim, not mine) would be thrown off by a web search?

Unless the creators of LLMs admit that their systems won’t achieve AGI by just throwing more money at it, shitty claims will prevent the field from actual progress.

Do you know many PhDs? Being thrown off by a web search isn’t that unbelievable.

Half the ones I know can barely operate their email

Only three if I’m being honest, and none of them technically competent, so I’ll admit that you have a point here. I’ll just add that I assume that Sam Altman had something different in mind when he made that claim.

agreed. he did.

my comment was mostly about PhD level being a nonsense term when speaking about general intelligence rather than depth of knowledge in a specific field