News for hackers. Stuff that matters.
Re:What Comes After AGI? by kenjackson on Friday November 20, 2026 @07:37AM (#50573850)
It seems like your definition of AGI is too focused on implementation details. IMO it has to be focused on behavior. Once you say something like “the weights do not change” then I think we’ve lost the plot. Instead say this is what an intelligent being can do, but a GenAI cannot.
Re:What Comes After AGI? by imtringued on Friday November 20, 2026 @08:03AM (#50574133)
I don't get it. Weights don't change means the model can't learn.

This is not merely an implementation detail, continual learning is the core of AGI.

Re:What Comes After AGI? by brainwad on Friday November 20, 2026 @08:42AM (#50574527)
It means the weights by themselves can't learn. But they could be used in a harness that can learn in other ways. Insisting that it be done at the neural net level seems anthropocentric - because we form memories via neural connections, that everything else must, too.

Also: I wouldn't say a human with amnesia who relied on notes to their future selves lacks intelligence, so I'm not sure being able to form memories is in fact necessary.

Re:What Comes After AGI? by ranyume on Friday November 20, 2026 @09:08AM (#50574861)
Even with a harness, there are things LLMs can't do. e.g. Write 50 entertaining short stories, each one completely different from the other but all sharing one motif.
Re:What Comes After AGI? by brainwad on Friday November 20, 2026 @12:43PM (#50578792)
That task sounds like something that at very least most humans couldn't do either and possibly is outright impossible (completely different yet sharing the same motif?).
Re:What Comes After AGI? by HarHarVeryFunny on Friday November 20, 2026 @08:12AM (#50574206)
I agree that definitions of intelligence should be based on capability rather than implementation, but given that we're discussing LLMs where the intelligence is in the weights, then "the weights don't change" can obviously be taken as pointing out that the model can't learn - the best it can do is memorize and load memorized stuff into context.

Memorizing facts is not the same as learning skills. Implementation-wise memorization can just be RAG, but learning does need to be in the "weights" - whatever it driving the actual behavior of the model.

Re:What Comes After AGI? by kenjackson on Friday November 20, 2026 @01:32PM (#50579557)
Again, I'd base this on capability. For example, you state: "Memorizing facts is not the same as learning skills." Maybe it's not. I'm not convinced it's not. In the ChatGPT 4 days (or so), I taught the instance I used some chess tactics/strategy that it didn't seem to know. And it appeared to use them correctly after that. Now you might note that this isn't really learning -- they just memorized it and then applied it appropriately.

With a sufficiently large context window, can you make a lot of things look like learning. And if it's not sufficient then point out the capabilities that aren't possible with this approach. To me that much more convincing.