←back to thread

Ask HN: Any insider takes on Yann LeCun's push against current architectures?

385 points vessenes | 1 comments | 10 Mar 25 19:41 UTC | HN request time: 0.405s | source

So, Lecun has been quite public saying that he believes LLMs will never fix hallucinations because, essentially, the token choice method at each step leads to runaway errors -- these can't be damped mathematically.

In exchange, he offers the idea that we should have something that is an 'energy minimization' architecture; as I understand it, this would have a concept of the 'energy' of an entire response, and training would try and minimize that.

Which is to say, I don't fully understand this. That said, I'm curious to hear what ML researchers think about Lecun's take, and if there's any engineering done around it. I can't find much after the release of ijepa from his group.

Show context
eximius ◴[14 Mar 25 21:31 UTC] No.43367519[source]▶
I believe that so long as weights are fixed at inference time, we'll be at a dead end.

Will Titans be sufficiently "neuroplastic" to escape that? Maybe, I'm not sure.

Ultimately, I think an architecture around "looping" where the model outputs are both some form of "self update" and "optional actionality" such that interacting with the model is more "sampling from a thought space" will be required.

replies(3): >>43367644 #>>43370757 #>>43372112 #
1. chriskanan ◴[15 Mar 25 12:29 UTC] No.43372112[source]▶
I 100% agree with this and sampling from thought space rather than "thinking" in terms of language. I spent forever writing up an NSF grant proposal on exactly this idea and submitted it last May. I haven't heard back, but it probably won't be funded.