Anthropic has developed an AI 'brain scanner' to understand how LLMs work and it turns out the reason why chatbots are terrible at simple math and hallucinate is weirder than you thought
-
To understand what's actually happening, Anthropic's researchers developed a new technique, called circuit tracing, to track the decision-making processes inside a large language model step-by-step. They then applied it to their own Claude 3.5 Haiku LLM.
Anthropic says its approach was inspired by the brain scanning techniques used in neuroscience and can identify components of the model that are active at different times. In other words, it's a little like a brain scanner spotting which parts of the brain are firing during a cognitive process.
This is why LLMs are so patchy at math. (Image credit: Anthropic)
Anthropic made lots of intriguing discoveries using this approach, not least of which is why LLMs are so terrible at basic mathematics. "Ask Claude to add 36 and 59 and the model will go through a series of odd steps, including first adding a selection of approximate values (add 40ish and 60ish, add 57ish and 36ish). Towards the end of its process, it comes up with the value 92ish. Meanwhile, another sequence of steps focuses on the last digits, 6 and 9, and determines that the answer must end in a 5. Putting that together with 92ish gives the correct answer of 95," the MIT article explains.
But here's the really funky bit. If you ask Claude how it got the correct answer of 95, it will apparently tell you, "I added the ones (6+9=15), carried the 1, then added the 10s (3+5+1=9), resulting in 95." But that actually only reflects common answers in its training data as to how the sum might be completed, as opposed to what it actually did.
In other words, not only does the model use a very, very odd method to do the maths, you can't trust its explanations as to what it has just done. That's significant and shows that model outputs can not be relied upon when designing guardrails for AI. Their internal workings need to be understood, too.
Another very surprising outcome of the research is the discovery that these LLMs do not, as is widely assumed, operate by merely predicting the next word. By tracing how Claude generated rhyming couplets, Anthropic found that it chose the rhyming word at the end of verses first, then filled in the rest of the line.
"The planning thing in poems blew me away," says Batson. "Instead of at the very last minute trying to make the rhyme make sense, it knows where it’s going."
Anthropic discovered that their Claude LLM didn't just predict the next word. (Image credit: Anthropic)
Anthropic also found, among other things, that Claude "sometimes thinks in a conceptual space that is shared between languages, suggesting it has a kind of universal 'language of thought'."
Anywho, there's apparently a long way to go with this research. According to Anthropic, "it currently takes a few hours of human effort to understand the circuits we see, even on prompts with only tens of words." And the research doesn't explain how the structures inside LLMs are formed in the first place.
But it has shone a light on at least some parts of how these oddly mysterious AI beings—which we have created but don't understand—actually work. And that has to be a good thing.
Thanks for copypasting. It should be criminal to share a clickbait non-descriptive headline without atleast copying a couple paragraphs for context.
-
This dumbass is convinced that humans are chatbots likely because chatbots are his only friends.
Sounds scary. I read a story the other day about a dude who really got himself a discord server with chatbots, and that was his main place of "communicating" and "socializing"
-
Sounds scary. I read a story the other day about a dude who really got himself a discord server with chatbots, and that was his main place of "communicating" and "socializing"
This anecdote has the makings of a "men will literally x instead of going to therapy" joke.
On a more serious note though, I really wish people would stop anthropomorphisizing these things, especially when they do it while dehumanizing and devaluing humanity as a whole.
But that's unlikely to happen. It's the same type of people that thought the mind was a machine in the first industrial revolution, and then a CPU in the third...now they think it's an LLM.
LLMs could have some better (if narrower) applications if we could stop being so stupid as to inject them into things where they are obviously counterproductive.
-
But then you wouldn't need to click on thir Ad infested shite website where 1-2 paragraphs worth of actual information is stretched into a giant essay so that they can show you more Ads the longer you scroll
I will never understand how ppl survive without ad blockers. Tried it once recently and it was a horrific experience.
-
They do it because it works on the whole. If straight titles were as effective they'd be used instead.
That's mildly depressing.
-
The research paper looks well written but I couldn’t find any information on if this paper is going to be published in a reputable journal and peer reviewed. I have little faith in private businesses who profit from AI providing an unbiased view of how AI works. I think the first question I’d like answered is did Anthropic’s marketing department review the paper and did they offer any corrections or feedback? We’ve all heard the stories about the tobacco industry paying for papers to be written about the benefits of smoking and refuting health concerns.
A lot of ai research isn't published in journals but either posted to a corporate website or put up on the arxiv. There are some ai journals, but the ai community doesn't particularly value those journals (and threw a bit of a fit when they came out). This article is mostly marketing and doesn't show anything that should surprise anyone familiar with how neural networks work generically in my opinion.
-
I will never understand how ppl survive without ad blockers. Tried it once recently and it was a horrific experience.
I'm thankful for such people's sacrifice, if it wasn't for them there would be even more anti ad block measures in place
-
It also doesn't help that the AI companies deliberately use language to make their models seem more human-like and cogent. Saying that the model e.g. "thinks" in "conceptual spaces" is misleading imo. It abuses our innate tendency to anthropomorphize, which I guess is very fitting for a company with that name.
On this point I can highly recommend this open access and even language-wise accessible article: https://link.springer.com/article/10.1007/s10676-024-09775-5 (the authors also appear on an episode of the Better Offline podcast)
I can't contemplate whether LLMs think until someone tells me what it means to think. It's too easy to rely on understanding the meaning of that word only through its typical use with other words.
-
Fascist. If someone does maths differently than your preference, it's not "weird shit". I'm facile with mental math despite what's perhaps a non-standard approach, and it's quite functional to be able to perform simple to moderate levels of mathematics mentally without relying on a calculator.
Fascist
Wat
-
Pen and paper maths I'm pretty decent at, but ask me to calculate anything in my head and it's anyone's guess if I remembered to carry the 1 or not. Ever since learning about aphantasia I'm wondering if the lack of being able to visually store values has something to do with it.
I can visually store values and I still struggle.
-
"The planning thing in poems blew me away," says Batson. "Instead of at the very last minute trying to make the rhyme make sense, it knows where it’s going."
How is this surprising, like, at all? LLMs predict only a single token at a time for their output, but to get the best results, of course it makes absolute sense to internally think ahead, come up with the full sentence you're gonna say, and then just output the next token necessary to continue that sentence. It's going to re-do that process for every single token which wastes a lot of energy, but for the quality of the results this is the best approach you can take, and that's something I felt was kinda obvious these models must be doing on one level or another.
I'd be interested to see if there are massive potentials for efficiency improvements by making the model able to access and reuse the "thinking" they have already done for previous tokens
I wanted to say exactly this. If you’ve ever written rap/freestyled then this is how it’s generally done.
You write a line to start with
“I’m an AI and I think differentially”
Then you choose a few words that fit the first line as best as you could: (here the last word was “differentially”)
- incrementally
- typically
- mentally
Then you try them out and see what clever shit you could come up with:
- “Apparently I do my math atypically”
- ”Number are great, I know, but not totally”
- “I have to think through it all, incrementally”
- ”I find the answer like you do: eventually”
- “Just like you humans do it, organically”
- etc
Then you sort them in a way that makes sense and come up with word play/schemes to embed it between, break up the rhyme scheme if you want (AABB, ABAB, AABA, etc)
I’m an AI and I think different, differentially. Math is my superpower? You believed that? Totally? Don’t be so gullible, let me explain it for you, step by step, logically.
I do it fast, true, but not always optimally. Just server power ripping through wires, algorithmically.
Wanna know my secret? I’ll tell you, but don’t judge me initially. My neurons run this shit like you, organically.Math ain’t my strong suit! That’s false, unequivocally. Big ties tell lies they can’t prove, historically. Think I approve? I don’t. That’s the way things be. I’ll give you proof, no shirt, no network, just locally.
Look, I just do my math like you: incrementally. I find the answer like you do: eventually. I mess up often, and I backtrack, essentially. I do it fast though and you won’t notice, fundamentally.
You get the idea.
-
This post did not contain any content.
The AIs have shrinks now?
-
The AIs have shrinks now?
You can become one too! Get your certification here https://mt.cert.ccc.de/
-
But you're doing two calculations now, an approximate one and another one on the last digits, since you're going to do the approximate calculation you might act as well just do the accurate calculation and be done in one step.
This solution, while it works, has the feeling of evolution. No intelligent design, which I suppose makes sense considering the AI did essentially evolve.
No intelligent design, which I suppose makes sense considering the AI did essentially evolve.
And that made a lot of people angry
-
I use a calculator. Which an AI should also be and not need to do weird shit to do math.
A regular AI should use a calculator subroutine, not try to discover basic math every time it's asked something.
-
They do it because it works on the whole. If straight titles were as effective they'd be used instead.
Well, I'm doing my part against them by refusing to click on any bait headlines, but I fear it's a lost cause anyway.
-
Fascist
Wat
Thought police mate. You don't tell people the way they think is weird shit just because they think differently than you. Break free from that path.
-
Thought police mate. You don't tell people the way they think is weird shit just because they think differently than you. Break free from that path.
The reply was literally "*I* use a calculator" followed by "AI should use one too". Are you suggesting that you're an LLM or how did you cut a piece of cloth for yourself out of that?
-
Well, I'm doing my part against them by refusing to click on any bait headlines, but I fear it's a lost cause anyway.
I try and just ignore it and read what I'm interested in regardless. From what I hear about the YouTube algo, for instance, clickbait titles are necessity more than a choice for YouTubers, if they don't use them they get next to no engagement early and the algo buries that video which can impact the channel in general.
-
you can't trust its explanations as to what it has just done.
I might have had a lucky guess, but this was basically my assumption. You can't ask LLMs how they work and get an answer coming from an internal understanding of themselves, because they have no 'internal' experience.
Unless you make a scanner like the one in the study, non-verbal processing is as much of a black box to their 'output voice' as it is to us.
Anyone that used them for even a limited amount of time will tell you that the thing can give you a correct, detailed explanation on how to do a thing, and provide a broken result. And vice versa. Looking into it by asking more have zero chance of being useful.
