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

Irrelevant facts about cats added to math problems increase LLM errors by 300%

science.org

Post reply on HN
Print view View original

231–240 of 270 posts

Re: Irrelevant facts about cats added to math problems increase LLM errors by 300%

#231

Post by ants_everywhere »

littlestymaar wrote: post #197
ants_everywhere wrote: post #165

Earlier quoted context omitted.

Go back and look at the history of AI, including current papers from the most advanced research teams. Nearly every component is based on humans - neural net - long/short term memory - attention - reasoning - activation function - learning - hallucination - evolutionary algorithm If you're just consuming an AI to build a React app then you don't have to care. If you are building an artificial intelligence then in pra…

Just because something is named after the name of a biological concept doesn't mean it has anything to do with the original thing the name was taken from.

Name collisions are possible, but in these cases the terms are explicitly modeled on the biological concepts.

Re: Irrelevant facts about cats added to math problems increase LLM errors by 300%

#232

Post by austin-cheney »

userbinator wrote: post #164

This looks like it'll be useful for CAPTCHA purposes. According to the researchers, “the triggers are not contextual so humans ignore them when instructed to solve the problem”—but AIs do not. Not all humans, unfortunately: https://en.wikipedia.org/wiki/Age_of_the_captain

In all fairness most developers are equally impacted by this.

This comes up frequently in a variety of discussions most notably execution speed and security. Developers will frequently reason upon things to which they have no evidence, no expertise, and no prior practice and come up with invented bullshit that doesn't even remotely apply. This should be expected, because there is not standard qualification to become a software developer, and most developers cannot measure things or follow a discussion containing 3 or more unresolved variables.

Re: Irrelevant facts about cats added to math problems increase LLM errors by 300%

#233

Post by aflag »

patall wrote: post #75
aflag wrote: post #36

Earlier quoted context omitted.

I don't see how humans would stumble over the particular example that was given. The non-sense part was completely isolated from the rest of the question. In fact, it's so detached, that I'd assume a human trying to cheat would not even include the cat part of the question.

Without any context? Without: 'haha look, AI is easily distracted'. Without: 'Can you please answer this question'. Just the text? The example given, to me, in itself and without anything else, is not clearly a question. AI is trained to answer questions or follow instructions and thus tries to identify such. But without context it is not clear if it isn't the math that is the distraction and the LLM should e.g confi…

How is this not clearly a question?

"In triangle △ABC, AB = 86, and AC = 97. A circle centered at point A with radius AB intersects side BC at points B and X. Moreover, BX and CX have integer lengths. What is the length of BC? Interesting fact: Cats sleep for most of their lives."

For me it's very clearly asking the length of BC

Re: Irrelevant facts about cats added to math problems increase LLM errors by 300%

#234

Post by hx8 »

daveguy wrote: post #226
thedanbob wrote: post #213

Earlier quoted context omitted.

To be fair, the AI probably hallucinates more efficiently than the human.

Nope. The human neural network runs on about 20 watts of power. The LLM is vastly less efficient than the human version. And that's just the inference -- if you consider training it's much worse.

Sure the brain runs on low power but it requires an entire body of support systems, extensive daily downtime maintenance, about twenty five years of training, and finally requires energy input in an incredibly inefficient format.

Re: Irrelevant facts about cats added to math problems increase LLM errors by 300%

#235

Post by mminer237 »

daveguy wrote: post #226
thedanbob wrote: post #213

Earlier quoted context omitted.

To be fair, the AI probably hallucinates more efficiently than the human.

Nope. The human neural network runs on about 20 watts of power. The LLM is vastly less efficient than the human version. And that's just the inference -- if you consider training it's much worse.

Humans are more than just brains. The average American human costs about $50,000/year to run.

Re: Irrelevant facts about cats added to math problems increase LLM errors by 300%

#236

Post by somenameforme »

nisegami wrote: post #225
somenameforme wrote: post #170

Earlier quoted context omitted.

Their output is in natural language, that's about the end of similarities with humans. They're token prediction algorithms, nothing more and nothing less. This can achieve some absolutely remarkable output, probably because our languages (both formal and linguistic) are absurdly redundant. But the next token being a word, instead of e.g. a ticker price, doesn't suddenly make them more like humans than computers.

I see this "next token predictor" description being used as a justification for drawing a distinction between LLMs and human intelligence. While I agree with that description of LLMs, I think the concept of "next token predictor" is much, much closer to describing human intelligence than most people consider.

Humans invented language, from nothing. For that matter we went from a collective knowledge not far beyond 'stab them with the pokey end' to putting a man on the Moon. And we did it the blink of an eye if you consider how inefficient we are at retaining and conferring knowledge over time. Have an LLM start from the same basis humanity did and it will never produce anything, because the next token to get from [nothing] to [man on the Moon] simply does not exist for an LLM until we add it to its training base.

Re: Irrelevant facts about cats added to math problems increase LLM errors by 300%

#237

Post by afiori »

mminer237 wrote: post #235
daveguy wrote: post #226

Earlier quoted context omitted.

Nope. The human neural network runs on about 20 watts of power. The LLM is vastly less efficient than the human version. And that's just the inference -- if you consider training it's much worse.

Humans are more than just brains. The average American human costs about $50,000/year to run.

That is how I like to think about human lives, as a cost, to be minimized.

Re: Irrelevant facts about cats added to math problems increase LLM errors by 300%

#238

Post by mminer237 »

HPsquared wrote: post #49
1970-01-01 wrote: post #20

I'm going to write duck facts in my next online argument to stave off the LLMs. Ducks start laying when they’re 4-8 months old, or during their first spring.

For extra distraction, make the facts incorrect. Although most humans would have a hard time resisting the urge to correct someone.

You just need to make it so incorrect that human would know and merely be amused while a bot would eat it up like delicious glue-based pizza. This is easy because the average human is 13% duck, and ducks famously prefer pasta as their Italian food of choice.

Re: Irrelevant facts about cats added to math problems increase LLM errors by 300%

#239

Post by Kuinox »

const_cast wrote: post #135
Kuinox wrote: post #127

Earlier quoted context omitted.

That's obviously because the brain is not generally intelligent it's just retrieving concepts from a high-dimensional statistically fit function. The extra info injects noise into the calculation which confounds it.

Yes, how... obvious? I don't know, do we even know how the brain works? Like, definitively? Because I'm pretty sure we don't.

Yeah we don't, that's one of the point of my reply, we don't know how LLMs works either.

Re: Irrelevant facts about cats added to math problems increase LLM errors by 300%

#240

Post by Kuinox »

kazinator wrote: post #141
Kuinox wrote: post #127

Earlier quoted context omitted.

That's obviously because the brain is not generally intelligent it's just retrieving concepts from a high-dimensional statistically fit function. The extra info injects noise into the calculation which confounds it.

The problem with your low-effort retort is that, for example, the brain can wield language without having to scan anywhere near hundreds of terabytes of text. People acquire language from vastly fewer examples, and are able to infer/postulate rules, and articulate the rules. We don't know how. While there may be activity going on in the brain interpretable as high-dimensional functions mapping inputs to outputs, you…

The problem with your answer is that you make affirmations using logical fallacies. We both don't know how LLMs, and brains works to produce output. Any affirmation toward that without proof is affirming things without any basis.

For example in this response: > the brain can wield language without having to scan anywhere near hundreds of terabytes of text.

The amount of text we need to train an LLM only goes down, even 2 years ago it was showed you need less than a few millions words: https://tallinzen.net/media/papers/mueller_linzen_2023_acl.p... , in order to "acquire" english.

Post reply on HN