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

21–30 of 197 posts

Re: Models Are Getting Dumber on Purpose

#21

Post by ismael_rr »

stefan_ wrote: post #5

I hope there is interesting research being done to stop models from 9B to 3T from authoritatively giving the wrong answers to factual questions instead of doing tool calls, but this article will tell you nothing about it. That's because it's clearly prompted by someone who simply noticed this deficiency very obvious to all practitioners and even users.

In my experience, it feels like this problem has been mostly solved. When I interact with a chatbot, I see it often uses web search to answer my questions and hallucinates much less then they used to. Furthermore, I suspect a lot of gains are merely from the system prompt instructing the chatbot to use web search to verify all facts it says.

Re: Models Are Getting Dumber on Purpose

#22

Post by kalb_almas »

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…

I would love this but I think the General Reasoning and Make No Mistakes modules would be massive.

Re: Models Are Getting Dumber on Purpose

#23

Post by hypfer »

Man, both that Blogpost and some comments here read like science-fiction.

Specifically, creative writing driven by nerds dreaming about a future, without proper grounding in reality, constraints and all that stuff.

Which is kinda ironic given the topic. And also important to do, because we should keep dreaming. We should just also be aware of when we are doing that and mark it as such.

Re: Models Are Getting Dumber on Purpose

#24

Post by scld »

edgyquant wrote: post #18
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 would defeat the AGI narrative/belief that so many building these models have

On the otherhand, your own brain probably doesn't use your eyes to hear.

Re: Models Are Getting Dumber on Purpose

#25

Post by kennywinker »

locknitpicker wrote: post #12
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. Aren't you describing RAG or even MCP servers? Heck, nowadays you get that also with agent skills and specialized tool calling.

I don't think so?

Definitely not MCP, as that pulls info into the context. Unless contexts become REALLY big so that I can add 10B in swift knowledge, that's not gonna help me.

Possible RAG? I don't know enough about how that works, but I think that's not quite it either. I don't want to import facts like "the swift standard library contains a reverse array function", i more want to import knowledge - e.g. the parameters used to generate the text to reverse an array in swift.

Tool calling wouldn't do it either. You'd have to encode every single possible bit of useful info into the tool call, and the tool response would have to encode every piece as well (variable names, function scopes, types defined in other files, etc). E.g. how does it find a bug, if you have to pass understanding back and forth between the brain that understands debugging and the brain that understands THIS code?

Re: Models Are Getting Dumber on Purpose

#26

Post by msdz »

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.

Generally I agree, with two caveats/thoughts:

Providing not just any a baseline, but a correct and useful one, is ever more important the less the model is grounded in world knowledge – misunderstandings probably compound faster if there is no general grasp of (broadly) “life on earth”, or computers, or whatever.

And secondly, I think (consumer-oriented) search becoming worse and worse is a challenge that’s mostly solvable (but far from solved!) for the big labs: (Mostly) trusted or even editorialized/reviewed sources like published work, Wikipedia, etc. is something they could index internally, it doesn’t need to come from a random blog site on the public internet. Furthermore, there’s a whole slew of companies specializing in crawling-for-LLM (i.e., bypassing bot protections) now as well.

Re: Models Are Getting Dumber on Purpose

#27

Post by E-Reverance »

edgyquant wrote: post #18
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 would defeat the AGI narrative/belief that so many building these models have

Would it? AGI was always about the efficiency gains of versatility, not strictly all forms of efficiency

Re: Models Are Getting Dumber on Purpose

#29

Post by cyanydeez »

E-Reverance wrote: post #27
edgyquant wrote: post #18

Earlier quoted context omitted.

This would defeat the AGI narrative/belief that so many building these models have

Would it? AGI was always about the efficiency gains of versatility , not strictly all forms of efficiency

AGI is whateve rmakes the VC open their wallet.

Re: Models Are Getting Dumber on Purpose

#30

Post by gopalv »

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…

> I want to click together a model that is laser-focused on what I am doing

This is roughly what multi-agent systems are built for.

This is possible with models too, but "making one on the fly" is much easier with agent coordination rather than model weights, since they all speak the same language.

There is an IBM Mainframe vs Google Distributed system division here. Like Seymour Cray said - two oxen or 1024 chickens.

Chickens are harder to harness, so a lot of my work is in sled-dog territory for agent harnesses & command structures.

Post reply on HN