Hacker News Reader

Comment by aqme28 | Hacker News Reader

It seems to me like these long context lengths are going to make a huge difference in the capabilities of things people are able to produce. Agents can use LLMs to subdivide a large corpus into manageable chunks. More context just makes them much much better at that.

Regardless, for most programming tasks, I doubt my equivalent human context length is any better than 32k tokens.

View on HN

'Superhuman' has many dimensions. It can be speed, it can be ability to retain a lot of information, it can be the ability to deal with a large quantity of information at once and many other dimensions besides. For the longest time Chess was considered a domain where computers could be dilettantes but could never dominate. Chess is now in 'superhuman' territory and likely we will never see a reversal because any insight that benefits humans also benefits computers but not the other way around.

The fact that this is such a multi-dimensional problem is frequently overlooked in the debate about AI/AGI etc, it may not matter all that much if the non AGI AI is already superhuman on enough dimensions other than the ones that the 'but it isn't AGI' crowd cling to. The consequences are what matters, not the fine print or the implementation details, and those consequences are directly tied to the number of dimensions along which a computer can beat humanity.

To give an example: if a chess program was 3000 Elo before but so slow that it would lose under competition rules then humans still dominated chess. Likewise if it would be only 2500 Elo but fast enough, it would still lose from the best humans. But for a large fraction of society it would have already moved out into 'superhuman' territory. And a couple of technological leaps of progress later and we're all looking at that AI as if it has moved into superhuman regions.

This sort of thing will happen on many fronts, and all of those fronts are moving, if enough of them go past the threshold then whether it is AGI or not is irrelevant and for every person that threshold is at different points. Maybe a computer will be able to calculate faster and better than you can, maybe it will be able to translate text faster and better than you, maybe it will be able to organize information faster and better than you. At which point we cross the line into saying that it can think faster and better than you is hard, but we can see that we are getting close to that line without even knowing exactly where that line is.

"Chess is now in 'superhuman' territory and likely we will never see a reversal because any insight that benefits humans also benefits computers but not the other way around."

What is considered human is malleable. It is conceivable that humans will be enhanced in various biological and non-biological ways to a point that they can once again compete with computers.

We may also just change the rules of chess.

"Chess" is a human created game after all.

Look I found the guy who keeps moving the goalposts!

It's a pretty common way for humans to deal with not being able to do something/something not working.

I think you're making a joke.

But moving goalposts is an integral part of all professional sports. The 3 point line in basketball and engine size and aspiration in motorsports are obvious examples. I don't see how adjusting chess rules to dis-favor AI competitors is any different.

Somebody actually tried with https://en.m.wikipedia.org/wiki/Arimaa, but it didn't last too long until it was also figured out!

I'm curious what kind of rule changes that could be made that would make Chess harder for deep neural networks?

I'm curious, what is the point your trying to convey?

> if a chess program was 3000 Elo before but so slow that it would lose under competition rules then humans still dominated chess.

How are you working out that it has a 3000 Elo if it's not winning games?

That's the way it is done right now: by playing it against other software implementations and judging them in the exact same way they would judge humans.

Stockfish has an Elo rating over 3500 in spite of no human being even close to that.

Is like a CPU, we’ve all seen that movie before, it’s super human in calculating numbers, it’s one dimensional nonetheless like chess programs.

One dimension that I think is pretty important is compute cost due to its effect on how they’re used. The chatbots are expensive to run, which means they’re implemented as request-response API’s that cost money, which means that loops are expensive and they normally don’t do any idle-time thinking.

When you play a turn-based game with a bot, that means you don’t need to worry about its reaction time. It’s paused most of the time, waiting on you. A sorcerer’s apprentice scenario isn’t going to happen when you’re single-stepping.

Moving to routine use of bots that run continuously with fast reaction times will be much more dangerous.

Yes, that's a very good point. Effectively it is 'ping pong' right now, when you get to always on + push things will change quite a bit. Model efficiency is a very active field.

> For the longest time Chess was considered a domain where computers could be dilettantes but could never dominate

I don't think this was ever true. Chess programs appeared EXTREMELY early in, and everyone recognised that it was a matter of time until hardware was quick enough to evaluate so many positions per second that grandmasters could be defeated by sheer calculation.

I was playing chess pretty fanatically when Sargon came out and that was my impression as a computer person, but the chess people around me really didn't think that computers would ever beat the top GMs.

Most major advances are predicted by someone, and often seem obvious in hindsight, but it seems like we often conflate those and remember them having been obvious before they happened.

The number of people working with computers back then was but a handful so that gave me a bit of a different perspective but I think that anybody that was both into computers and into chess back then would have made the same prediction. It still happened faster than I thought it would.

The problem with comparing LLM and human context length is that LLMs don't update their weights based on their input. The 32k of context that they do have is their only memory.

Humans have multiple layers of memory and can recall things and concepts from years in the past - akin to millions of tokens' worth of recall in an LLM. Yes, that memory is extremely lossy, but it's there.

The problem is not the short term context length, but long term. If you want to do things like long term goal planning, keeping track of distant past events can be of high value

I’d argue for planning that the answer is to couple the LLM to some other system rather than try to improve the LLM. Combinatorial optimization is a well-understood problem that is NP-complete in theory but practical to solve in practice. For doing math we might as well give the LLM a pocket calculator, why not couple it to a planner, theorem prover and similar tools?

This is pretty much what people are testing now with Auto-GPT

"For doing math we might as well give the LLM a pocket calculator, why not couple it to a planner, theorem prover and similar tools?"

ChatGPT has already been hooked up to Wolfram Alpha.[1]

For hooking up other things, see HuggingGPT and TaskMatrix.AI.[2][3]

[1] - https://writings.stephenwolfram.com/2023/03/chatgpt-gets-its...

[2] - https://arxiv.org/pdf/2303.17580.pdf

[3] - https://arxiv.org/pdf/2303.16434.pdf

Precisely. LLMs are the Perl of the future

That's the interesting thing. if LLM start to just become interfaces for other systems you could probably just use them to train smaller systems like in the style of alpaca and other recent LLMs.

Maybe that’s what our inner monologue is for… to cycle relevant context through regularly so it stays in scope. I mean, that’s not actually why we have one but it’d be cute.

Our context is hierarchical, at multiple different resolutions, so I don't think it's comparable.

Good chance so is OAI's https://arxiv.org/abs/2110.13711 (paper has the long context lead at OAI as a co-author)

I'd say when you're actively trying to remember an event and "narrowing it down" mentally is a process that feels suspiciously like a dialogue with an LLM where you keep asking for the answer to be improved.

I was trying to describe a hierarchy of LLMs as an agent. I don't think that's a uniquely human ability.

I've had good results using that approach with LLMs for domain-specific problem solving.

Human expert relies in the “chunking” effect for expertise, which is mostly not part of the context length (working memory). For a pseudo-analogy, each human is fine-tuned from the raw intelligence (by training and education). In that way generic LLM probably can’t beat us yet so don’t despair!

Any job focused on fact retrieval is at risk.

Need to know that the facts exist in the first place, though.

GPT-4 is already at a level that it has graduate level math and physics knowledge, with a level of recall that most students can only dream of.

Do those actually matter in jobs? Most valuable facts I encounter are far more niche, often in someone's head and not written down, only stored privately somewhere etc.

What kind of job is only focused on fact retrieval?

Jeopardy contestant

My bigget blocker in web development is fact retrieval. As someone who only dabbles, I don't struggle with how to logically design my project, but I'm constantly forgetting CSS and JS details like how to accomplish a specific task with CSS flexbox or how to sort an array in JS vs in Python. On old personal projects, I forget the names of my own functions and whether they return a list or a dict. Hell, I'll forget function signatures for functions I just wrote. I forget external library and API details. If I had perfect recall, I would 100x my web dev productivity.

Reply on news.ycombinator.com