Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Learning from context is harder than we thought

hy.tencent.com

Post reply on HN
Print view View original

41–50 of 140 posts

Re: Learning from context is harder than we thought

#41

Post by CorrectHorseBat »

com2kid wrote: post #35
4b11b4 wrote: post #31

Earlier quoted context omitted.

I'm not sure if you want models perpetually updating weights. You might run into undesirable scenarios.

If done right, one step closer to actual AGI. That is the end goal after all, but all the potential VCs seem to forget that almost every conceivable outcome of real AGI involves the current economic system falling to pieces. Which is sorta weird. It is like if VCs in Old Regime france started funding the revolution.

Yes the planet got destroyed. But for a beautiful moment in time we created a lot of value for shareholders.

And for your comparison, they did fund the American revolution which on its turn was one of the sparks for the French revolution (or was that exactly the point you were making?)

Re: Learning from context is harder than we thought

#42

Post by johnsmith1840 »

foobar10000 wrote: post #29
johnsmith1840 wrote: post #3

It's basically continual learning. This is beyond a hard problem it's currently an impossible one. I know of no system that solve CL even at small scale let alone large models. Annoyingly, they have SOME inherent capability to do it. It's really easy to get sucked down this path due to that glimmer of hope but the longer you play with it the more annoying it becomes. SSI seems to be focused on this problem directly s…

So, surprising, that is not completely true - I know of 2 finance HFT trading firms that do CL at scale, and it works - but in a relatively narrow context of predicting profitable actions. It is still very surprising it works, and the compute is impressively large to do it - but it does work. I do have some hope of it translating to the wider energy landscapers we want AI to work over…

During covid almost every prediction model like that exploded, everything went out of distribution really fast. In your sense we've been doing "CL" for a decade or more. It can also be cheap if you use smaller models.

But true CL is the ability to learn out of distribution information on the fly.

The only true solution I know to continual learning is to completely retrain the model from scratch with every new example you encounter. That technically is achievable now but it also is effectively useless.

Re: Learning from context is harder than we thought

#43

Post by charcircuit »

cs702 wrote: post #24

The problem is even more fundamental: Today's models stop learning once they're deployed to production. There's pretraining, training, and finetuning, during which model parameters are updated. Then there's inference, during which the model is frozen. "In-context learning" doesn't update the model. We need models that keep on learning (updating their parameters) forever, online, all the time.

Models like Claude have been trained to update and reference memory for Claude Code (agent loops) independently and as a part of compacting context. Current models have been trained to keep learning after being deployed.

Re: Learning from context is harder than we thought

#44

Post by 0xdeadbeefbabe »

4b11b4 wrote: post #31
cs702 wrote: post #24

The problem is even more fundamental: Today's models stop learning once they're deployed to production. There's pretraining, training, and finetuning, during which model parameters are updated. Then there's inference, during which the model is frozen. "In-context learning" doesn't update the model. We need models that keep on learning (updating their parameters) forever, online, all the time.

I'm not sure if you want models perpetually updating weights. You might run into undesirable scenarios.

How about we just put them to bed once in a while?

Re: Learning from context is harder than we thought

#45

Post by godelski »

winddude wrote: post #26
godelski wrote: post #19

It is weird to read because they bring up many things a lot of people have been critiquing for years. > But as impressive as these feats are, they obscure a simple truth: being a "test-taker" is not what most people need from an AI. > In all these cases, humans aren't relying solely on a fixed body of knowledge learned years ago. We are learning, in real-time, from the context right in front of us. > To bridge this g…

> But as impressive as these feats are, they obscure a simple truth: being a "test-taker" is not what most people need from an AI. People have been bringing that up long before AI, on how schooling often tests on memorization and regurgitation of facts. Looking up facts is also a large part of the internet, so it is something that's in demand, and i believe a large portion of openAI/cluade prompts have a big overlap…

Don't confuse what I'm saying, I do find LLMs useful. You're right, about knowledge based systems being useful and I'm not disagreeing with that in any way. I don't think any of the researchers claiming LLMs are not a viable path to AGI are. We're saying that intelligence is more than knowledge. Superset, not disjoint.

And yes, the LLM success has been an important step to AGI but that doesn't mean we can't scale it all the way there. We learned a lot about knowledge systems. That's a big step. But if you wonder why people like Chollet are saying LLMs have held AGI progress back it is because we put all our eggs in one basket. It's because we've pulled funds and people away from other hard problems to focus on only one. That doesn't mean it isn't a problem that needed to be solved (nor that it is solved) but that research slows or stops on the other problems. When that happens we hit walls as we can't seamlessly transition. I'm not even trying to say that we shouldn't have most researchers working on the problem that's currently yielding the most success, but the distribution right now is incredibly narrow (and when people want to work on other problems they get mocked and told that the work is pointless. BY OTHER RESEARCHERS).

Sure, you can get to the store navigating block by block, but you'll get there much faster, more easily, and better adapt to changes in traffic if you incorporate route planning. You would think a bunch of people who work on optimization algorithms would know that A* is a better algorithm than DFS. The irony is that the reason we do DFS is because people have convinced themselves that we can just keep going this route to get there but if more intellectual depth (such as diving into more mathematical understandings of these models) was taken then you couldn't be convinced of that.

Re: Learning from context is harder than we thought

#46

Post by com2kid »

CorrectHorseBat wrote: post #41
com2kid wrote: post #35

Earlier quoted context omitted.

If done right, one step closer to actual AGI. That is the end goal after all, but all the potential VCs seem to forget that almost every conceivable outcome of real AGI involves the current economic system falling to pieces. Which is sorta weird. It is like if VCs in Old Regime france started funding the revolution.

Yes the planet got destroyed. But for a beautiful moment in time we created a lot of value for shareholders. And for your comparison, they did fund the American revolution which on its turn was one of the sparks for the French revolution (or was that exactly the point you were making?)

The funding of the American revolution is a fun topic but most people don't know about it so I don't bother dropping references to it. :D

Re: Learning from context is harder than we thought

#47

Post by nemomarx »

cs702 wrote: post #33
4b11b4 wrote: post #31

Earlier quoted context omitted.

I'm not sure if you want models perpetually updating weights. You might run into undesirable scenarios.

Our brains, which are organic neural networks, are constantly updating themselves. We call this phenomenon "neuroplasticity." If we want AI models that are always learning, we'll need the equivalent of neuroplasticity for artificial neural networks. Not saying it will be easy or straightforward. There's still a lot we don't know!

How would you keep controls - safety restrictions - Ip restrictions etc with that, though? the companies selling models right now probably want to keep those fairly tight.

Re: Learning from context is harder than we thought

#48

Post by ra »

charcircuit wrote: post #43
cs702 wrote: post #24

The problem is even more fundamental: Today's models stop learning once they're deployed to production. There's pretraining, training, and finetuning, during which model parameters are updated. Then there's inference, during which the model is frozen. "In-context learning" doesn't update the model. We need models that keep on learning (updating their parameters) forever, online, all the time.

Models like Claude have been trained to update and reference memory for Claude Code (agent loops) independently and as a part of compacting context. Current models have been trained to keep learning after being deployed.

yes but that's a very unsatisfactory definition of memory.

Re: Learning from context is harder than we thought

#49

Post by vjerancrnjak »

johnsmith1840 wrote: post #3

It's basically continual learning. This is beyond a hard problem it's currently an impossible one. I know of no system that solve CL even at small scale let alone large models. Annoyingly, they have SOME inherent capability to do it. It's really easy to get sucked down this path due to that glimmer of hope but the longer you play with it the more annoying it becomes. SSI seems to be focused on this problem directly s…

Bandits?

Spaced repetition algos

Re: Learning from context is harder than we thought

#50

Post by raincole »

cs702 wrote: post #24

The problem is even more fundamental: Today's models stop learning once they're deployed to production. There's pretraining, training, and finetuning, during which model parameters are updated. Then there's inference, during which the model is frozen. "In-context learning" doesn't update the model. We need models that keep on learning (updating their parameters) forever, online, all the time.

> We need models that keep on learning (updating their parameters) forever, online, all the time.

Yeah, that's the guaranteed way to get MechaHilter in your latent space.

If the feedback loop is fast enough I think it would finally kill the internet (in the 'dead internet theory' sense). Perhaps it's better for everyone though.

Post reply on HN