Mmm. Wake me up when there’s 3rd party confirmation of these things that isn’t just a marketing ploy.
Emergent introspective awareness in large language models
Submitted 3 days ago by kromem@lemmy.world to technology@lemmy.world
https://www.anthropic.com/research/introspection
Comments
AwesomeLowlander@sh.itjust.works 3 days ago
kromem@lemmy.world 3 days ago
I tend to see a lot of discussion taking place on here that’s pretty out of touch with the present state of things, echoing earlier beliefs about LLM limitations like “they only predict the next token” and other things that have already been falsified.
This most recent research from Anthropic confirms a lot of things that have been shifting in the most recent generation of models in ways that many here might find unexpected, especially given the popular assumptions.
Specifically interesting are the emergent capabilities of being self-aware of injected control vectors or being able to silently think of a concept so it triggers the appropriate feature vectors even though it isn’t actually ending up in the tokens.
Telorand@reddthat.com 3 days ago
This is not a good source. This is effectively, “We’ve investigated ourselves and found [that AI is a miraculous wonder].” Anthropic has a gigantic profit incentive to shill AI, and you should demand impartiality and better data than this.
radix@lemmy.world 3 days ago
Check their account history. They may as well be on an AI company marketing team.
MagicShel@lemmy.zip 3 days ago
They aren’t “self-aware” at all. These thinking models spend a lot of turns coming up with chains of reasoning. They focus on the reasoning first, and their reasoning primes the context.
Like if I asked you to compute the area of a rectangle you might first say to yourself: “okay. There’s a formula for that. LxW. This rectangle is 4 by 5, so the calculation is 4x5, with is 20.” They use tokens to delineate the “thinking” from their response and only give you the response, but most will also show the thinking if you want.
In contrast, if you ask an AI how it arrived at an answer after it gives it, it needs to either have the thinking in context or it is 100% bullshitting you. The reason injecting a thought affects the output is because that injected thought goes into the context. It’s like if you’re trying to count cash and I shout numbers at you, you might keep your focus on the task or the numbers might throw off your response.
Literally all LLMs do is predict tokens, but we’ve gotten pretty good at finding more clever ways to do it. Most of the advancements in capabilities have been very predictable. I had a crude google augmented context before ChatGPT released browsing capabilities, for instance. Tool use is just low randomness, high confidence, model that the wrapper uses to generate shell commands that it then runs. That’s why you can ask it to do a task 100 times and it’ll execute 99 times correctly and then fail—got a bad generation.
My point is we are finding very smart ways of using this token prediction, but in the end that’s all it is. And something many researchers shockingly fail to grasp is that by putting anything into context—even a question—you are biasing the output. It simply predicts how it should respond to the question based on what is in its context. That is not at all the same thing as answering a question based on introspection or self-awareness. And that’s obviously the case because their technique only “succeeds” 20% of the time.
I’m not a researcher. But I keep coming across research like this and it’s a little disconcerting that the people inventing this shit sometimes understand less about it than I do. Don’t get me wrong, I know they have way smarter people than me, but anyone who just asks LLMs questions and calls themselves a researcher is fucking kidding.
I use AI all the time. I think it’s a great tool and I’m investing a lot of my own time into developing tools for my own use. But it’s a bullshit machine that just happens to spit out useful bullshit, and people are desperate for it to have a deeper meaning. It… doesn’t.
kromem@lemmy.world 3 days ago
So while your understanding is better than a lot of people on here, a few things to correct.
First off, this research isn’t being done on the models in reasoning mode, but in direct inference. So there’s no CoT tokens at all.
The injection is not of any tokens, but of control vectors. Basically it’s a vector which being added to the activations makes the model more likely to think of that concept. The most famous was “Golden Gate Claude” that had the activation for the Golden Gate Bridge increased so it was the only thing the model would talk about.
So, if we dive into the details a bit more…
If your theory was correct, then the way the research asks the question saying that there’s control vectors and they are testing if they are activated, then the model should be biased to sometimes say “yes, I can feel the control vector.” And yes, in older or base models that’s what we might expect to see.
But, in Opus 4/4.1, when the vector was not added, they said they could detect a vector… 0% of the time! So the control group had enough introspection capability as to not stochastically answer that there was a vector present when there wasn’t.
But then, when they added the vector at certain layer depths, the model was often able to detect that there was a vector activated, and further to guess what the vector was adding.
So again — no reasoning tokens present, and the experiment had control and experimental groups where the results negates your theory as to the premise of the question causing affirmative bias.
Again, the actual research is right there a click away, and given your baseline understanding at present, you might benefit and learn a lot from actually reading it.
rah@hilariouschaos.com 2 days ago
LLM limitations like “they only predict the next token” and other things that have already been falsified
What do LLMs do beyond predicting the next token?
kromem@lemmy.world 2 days ago
A few months back it was found that when writing rhyming couplets the model has already selected the second rhyming word when it was predicting the first word of the second line, meaning the model was planning the final rhyme tokens at least one full line ahead and not just predicting that final rhyme when it arrived at that token.
It’s probably wise to consider this finding in concert with the streetlight effect.
gravitas_deficiency@sh.itjust.works 3 days ago
Why should I give a single shit about this obviously self-promoting marketing drivel from Anthropic?