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

A global workspace in language models

anthropic.com

Post reply on HN
Print view View original

101–110 of 218 posts

Re: A global workspace in language models

#101

Post by nullbio »

greatgib wrote: post #40

I'm reading that probably too fast to have a deep thinking about it, but this J-Space isn't it just the basic of embedding vectors. If you think about getting from a place to another place, using wheels, no gas, to reply to the question of what to visit nearby, maybe in the vector space at the center of all of that you have the word "Bicycle" nearby, so obviously if you look at the value you would say that the model…

You're correct. It's just the latent space of the transformation. Nothing magical here, they're effectively breakpointing the model at the layer level and switching the activations in real time. It's pseudo-scientific bullshit designed to push a narrative.

Re: A global workspace in language models

#103

Post by varenc »

NotGMan wrote: post #30

>> None of this tells us whether Claude is conscious in the way people are, or whether it feels anything at all My problem with the entire "Is AI conscious" debate is that we don't even know what exactly consciousness in humans is. You need to understand something in order to compare it to something else. Otherwise you are just comparing different definitions and second order derived phenomena.

I don't think that quote from the article is disagreeing with you at all. Like you said, we don't have a cohesive definition or test of consciousness, so research like this doesn't say anything about if this is or isn't similar to human consciousness.

I would guess Anthropic included that sentence to make it very clear they're not claiming human-like consciousness, and dampen journalists writing headlines like "Anthropic discovers their AI thinks just like humans and may be conscious".

edit: later in the article they even more explicitly agree with you

> Our experiments don't show Claude can have experiences, or feel things in the way humans do—in fact, it’s unclear whether any scientific experiment could prove this to be true or false

Re: A global workspace in language models

#105

Post by horacemorace »

ACCount37 wrote: post #56
unleaded wrote: post #55

This reminded me of some weird quirk/experiment I found with LLMs that I found while messing around, maybe someone can explain it or something. Open any AI chatbot that isn't cheating by connecting to the Internet (so disable web search). Claude, DeepSeek, Kimi, whatever. Ask them this question: "What was that weird band from michigan from the 2000s that wore coloured ties" You will probably get a wrong answer, or if…

"The reversal curse", it rarely shows up in practice but you found a case when it did. The "knowledge landscape" an LLM uses is "directional". It's easy to reach "a quirky music band from Michigan known for colored ties" when you stand at "Tally Hall". But if you stand at "a quirky music band from Michigan known for colored ties", it's harder to reach "Tally Hall" from there. For the "latent knowledge graph" an LLM u…

If this kind of thing holds true for humans we now may understand synesthesia, perhaps we find ourselves with a large enough study pool to map out clever tricks to influence each other.

Re: A global workspace in language models

#106

Post by michaelhoney »

josh-sematic wrote: post #96
unleaded wrote: post #55

This reminded me of some weird quirk/experiment I found with LLMs that I found while messing around, maybe someone can explain it or something. Open any AI chatbot that isn't cheating by connecting to the Internet (so disable web search). Claude, DeepSeek, Kimi, whatever. Ask them this question: "What was that weird band from michigan from the 2000s that wore coloured ties" You will probably get a wrong answer, or if…

If I ask my kid (early elementary) what he learned last school year, I can watch him apparently genuinely trying to think of some examples and not being very successful. If I ask him something I know he learned he’ll gladly say “oh yeah!” and tell me about it.

dude, you could ask me, a grown adult, what I did last week and get a similar lack of recall

Re: A global workspace in language models

#107

Post by taosu_la »

The article says that this ability was discovered around opus 4.5, but open-source models like deepseek and glm have already surpassed the capabilities of opus4.5. But why hasn't this been discovered before? Is it because the scale of computing power is not large enough?

Re: A global workspace in language models

#109

Post by gwerbin »

wongarsu wrote: post #27
com2kid wrote: post #21

Anyone remember that blog post from a few months back where someone was able to improve a model's math ability by just duplicating layers that were activated while solving math problems? Just literally copy/pasting them and linking them together so the model ran through the same layers again? I get the feeling a lot more research is going to come out in the area of exploring exactly what portions of a model's weights…

Found it: https://news.ycombinator.com/item?id=47500709 Part 3 might be the best introduction: https://dnhkng.github.io/posts/sapir-whorf/ tl;dr: Based on experiments with similar prompts translated to different languages LLM layers group into three phases: the first decodes from the source language into an abstract space, the middle does something, then there's a last part where the abstract result gets transformed…

That's a cool result because that's also kind of what's happening inside the transformer unit: project -> QKV fuzzy lookup -> unproject. And in a different direction, it's analogous in some sense to what's happening in stacked convolutional layers, where the layers at different levels learn to recognize features of increasing detail.

Re: A global workspace in language models

#110

Post by muti »

devanshp wrote: post #58
unleaded wrote: post #55

This reminded me of some weird quirk/experiment I found with LLMs that I found while messing around, maybe someone can explain it or something. Open any AI chatbot that isn't cheating by connecting to the Internet (so disable web search). Claude, DeepSeek, Kimi, whatever. Ask them this question: "What was that weird band from michigan from the 2000s that wore coloured ties" You will probably get a wrong answer, or if…

https://claude.ai/share/2b0f85a2-e7b8-4f62-91a0-eca61bdeabec Fable 5 on low gets the answer with web search turned off, one-shot!

Thank you for prompting me to try with my own obscure question, Fable was able to find something from a poor description. I've been looking manually and over many sessions with different models as they improve, none have been able to find what I was after. Fable 5 just one-shot the answer.
Post reply on HN