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

Models Are Getting Dumber on Purpose

w4g1.dev

Post reply on HN
Print view View original

71–80 of 197 posts

Re: Models Are Getting Dumber on Purpose

#71

Post by kennywinker »

jimmaswell wrote: post #58
kennywinker wrote: post #4

Ideally what I'd like to see is pluggable knowledge bases. So if I'm e.g. coding a SwiftUI app for navigation, I'd take 9B of basic coding and reasoning, add 10B of swift/swiftUI, add 5B of GIS/geography knowledge and another 5B of frontend app design knowledge. My model doesn't need to know a single line of python. Then when I want to research electronics components, I grab a 15B model of agentic research techniques…

An LLM works better the more disparate world knowledge it has, even if it's not immediately obvious why it would be relevant. The model finds a structure to the problem you give it in a largely language-agnostic way that benefits from training on every language (these things are direct descendants of Google Translate), and even non-programming knowledge - the structure of your task might resemble an ancient Chinese p…

This makes a ton of sense, and seems like it's coming from somebody who understands LLMs better than I do so I will definitely take your word for it - but it doesn't totally track with my experience of running small local models either. In my experience some models are better at language X and others better at language Y - and all of them are better at language X and Y than language Z-I-just-made-up. I take that to mean there is some relationship between training data and skill. Maybe not enough to make pluggable modules, tho... at least not with the architectures we're currently using.

Re: Models Are Getting Dumber on Purpose

#72

Post by lowsong »

gagan2020 wrote: post #20

Intelligence vs Knowledge LLMs work is being intelligent not having knowledge of everything is ok. But, they have to be intelligent enough (with some degree of knowledge) that where to find the information (search tools or any other tools for that matter)

LLMs are not intelligent. Please don't anthropomorphize.

Re: Models Are Getting Dumber on Purpose

#73

Post by PaulStatezny »

xena wrote: post #54

This article is AI output.

Which is totally ironic, given that the article is largely about how untrustworthy LLMs can be. (Hallucination.)

Putting readers through this exercise disrespects their time. Even if as a writer you did the work of researching, reasoning, and fact-checking, you shoot yourself in the foot by running it through an LLM because there's no way for the reader to know which thoughts/research are from you. It demolishes the Ethos of the writing; readers feel they must do quality assurance on the reasoning, research, and facts.

Re: Models Are Getting Dumber on Purpose

#74

Post by kennywinker »

conartist6 wrote: post #32
kennywinker wrote: post #4

Ideally what I'd like to see is pluggable knowledge bases. So if I'm e.g. coding a SwiftUI app for navigation, I'd take 9B of basic coding and reasoning, add 10B of swift/swiftUI, add 5B of GIS/geography knowledge and another 5B of frontend app design knowledge. My model doesn't need to know a single line of python. Then when I want to research electronics components, I grab a 15B model of agentic research techniques…

This is going to be how I write my resume now: how many billion parameters of knowledge I have on each topic

...kennywinker is a 0.001B MoE model, with 2 active parameters.

Re: Models Are Getting Dumber on Purpose

#75

Post by redmacaw »

jimmaswell wrote: post #58
kennywinker wrote: post #4

Ideally what I'd like to see is pluggable knowledge bases. So if I'm e.g. coding a SwiftUI app for navigation, I'd take 9B of basic coding and reasoning, add 10B of swift/swiftUI, add 5B of GIS/geography knowledge and another 5B of frontend app design knowledge. My model doesn't need to know a single line of python. Then when I want to research electronics components, I grab a 15B model of agentic research techniques…

An LLM works better the more disparate world knowledge it has, even if it's not immediately obvious why it would be relevant. The model finds a structure to the problem you give it in a largely language-agnostic way that benefits from training on every language (these things are direct descendants of Google Translate), and even non-programming knowledge - the structure of your task might resemble an ancient Chinese p…

could you share the 3blue1brown videos you're referring to?

Re: Models Are Getting Dumber on Purpose

#76

Post by throwaway1492 »

kennywinker wrote: post #4

Ideally what I'd like to see is pluggable knowledge bases. So if I'm e.g. coding a SwiftUI app for navigation, I'd take 9B of basic coding and reasoning, add 10B of swift/swiftUI, add 5B of GIS/geography knowledge and another 5B of frontend app design knowledge. My model doesn't need to know a single line of python. Then when I want to research electronics components, I grab a 15B model of agentic research techniques…

> So if I'm e.g. coding a SwiftUI app for navigation, I'd take 9B of basic coding and reasoning, add 10B of swift/swiftUI, add 5B of GIS/geography knowledge and another 5B of frontend app design knowledge. My model doesn't need to know a single line of python.

Tell me you don’t know how llm work without telling me you don’t know how llm work. That’s not how they work!

Re: Models Are Getting Dumber on Purpose

#77

Post by ruszki »

pulkitsh1234 wrote: post #33

But is Reasoning and Facts truly separate ? To reason properly about the human condition (eg. World War) wouldn't you need to reason on some facts ? And then reason how some "facts" change the human behaviour ? How can you arrive via pure reasoning to predict how a collective of humans act ? We are not reasonable, humans are not logical deterministic machines confined to algebraic rules.

You can also reason the same way on some complete nonsense. A lot of us do this all the time.

Re: Models Are Getting Dumber on Purpose

#78

Post by jcfrei »

kennywinker wrote: post #13
msdz wrote: post #9

Great article, even if it will be interesting to see whether things continue to develop in such a direction or not. > There's a version of this future where the model card stops listing a knowledge cutoff at all, because what's left in the weights goes stale on a scale of years instead of weeks. Future? Even just recently I’ve read of two approaches to this problem: Cactus have come up with Needle [0][1], which is th…

That kind of setup is super dependent on a search engine, and search keeps getting worse.

search isnt that super hard to solve. the problem is that incentives are misaligned - which means companies who sell something have an incentive to share their index with the corporation that pays to be the default search provider. for a simple search engine that just delivers facts there's very little incentive to keep its index up-to-date: because that company wont get the apis to retrieve the content efficiently, so it needs more compute, bandwidth and storage to run.

Re: Models Are Getting Dumber on Purpose

#79

Post by pixelatedindex »

redmacaw wrote: post #75
jimmaswell wrote: post #58

Earlier quoted context omitted.

An LLM works better the more disparate world knowledge it has, even if it's not immediately obvious why it would be relevant. The model finds a structure to the problem you give it in a largely language-agnostic way that benefits from training on every language (these things are direct descendants of Google Translate), and even non-programming knowledge - the structure of your task might resemble an ancient Chinese p…

could you share the 3blue1brown videos you're referring to?

https://youtu.be/l6DKRf-fAAM maybe? Title is “Reinventing Entropy”

And of course the neural network series.

Re: Models Are Getting Dumber on Purpose

#80

Post by nubg »

good article but why did the author feel like he needed to "polish" it by running it through an LLM? i would rather like to read the actual prompt he put in there, as now i'm not sure which points are his, and which have been hallucinated!
Post reply on HN