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

71–80 of 218 posts

Re: A global workspace in language models

#71

Post by orbital-decay »

minimaltom wrote: post #15

This, taken in combination with the SAE paper, the golden-gate claude paper, the feelings / introspection paper, and note in the fable system card (that they are silently nerfing responses about activation shaping), is basically confirmation to me that they have a new technique they they are using during training (along the vibe space of these mechinterp papers), and its probably some kind of representation learning…

I'm sure Anthropic of all companies don't do that, since using mechinterp as a training target will make the the result uninterpretable.

Re: A global workspace in language models

#72

Post by throwitaway222 »

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…

Worried person cure: Stop overthinking it!

LLM -> AGI fix: START OVERTHINKING!

Re: A global workspace in language models

#73

Post by ACCount37 »

optimalsolver wrote: post #64
ACCount37 wrote: post #61

Earlier quoted context omitted.

Ah, that big model smell. Every time someone somewhere says "an LLM can't do this", the next generation of LLMs gains one more parameter. Until that LLM can, in fact, do this.

So the model was updated in the 37 minutes since OP posted his comment?

Just a funny observation. Every time someone proclaims "LLMs can't do X", a bigger, badder LLM that can in fact do X shows up shortly thereafter.

Clearly, Fable 5 didn't even have the decency to wait until the next model refresh cycle to show up. It was already sitting there waiting.

Either the capability gains in bigger, badder models are actually unrelated to "gotchas" being discovered, or LLMs are already acquiring Skynet levels of disrespect for cause and effect.

Re: A global workspace in language models

#74

Post by fasterik »

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…

This doesn't seem that weird to me. Talk to any human and you'll find that their ability to recall specific names and facts is very context-dependent. Phrasing a question in one way can make it hard to answer, while providing certain words or cues can instantly "jog" the memory.

Re: A global workspace in language models

#75

Post by appplication »

famouswaffles wrote: post #60
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…

Recall isn't naturally bidirectional, even for humans. If you are learning vocabulary in a new language, it's common advice to practice both target > source and source > target. Doing only one-way often makes you much better recalling that single direction than both.

I would need further convincing that humans do not naturally tend towards bidirectional recall.

Perhaps I’m just on alert anytime I see an LLM-ism that’s met with a claim that the same or similar phenomena holds true in humans as well.

Re: A global workspace in language models

#76

Post by unleaded »

ACCount37 wrote: post #73
optimalsolver wrote: post #64

Earlier quoted context omitted.

So the model was updated in the 37 minutes since OP posted his comment?

Just a funny observation. Every time someone proclaims "LLMs can't do X", a bigger, badder LLM that can in fact do X shows up shortly thereafter. Clearly, Fable 5 didn't even have the decency to wait until the next model refresh cycle to show up. It was already sitting there waiting. Either the capability gains in bigger, badder models are actually unrelated to "gotchas" being discovered, or LLMs are already acquirin…

I don't think it's solved this fundamental architectural problem by itself, it will have just squeezed the edge cases thinner. It keeps happening, people find a question it gets stupidly wrong, the vendors proclaim they've fixed it, then another one gets found.

Re: A global workspace in language models

#77

Post by hasteg »

kgeist wrote: post #57
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…

Probably an instance of: "The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A" https://arxiv.org/abs/2309.12288

Really interesting paper, thanks for the share.

The point their making in that paper reminds me of this paper some people shared around work earlier this year, https://arxiv.org/pdf/2512.14982 (Prompt Repetition Improves Non-Reasoning LLMs)... I wonder how OPs question would fare (or the questions presented in the paper you posted) given double repetition.

Re: A global workspace in language models

#78

Post by famouswaffles »

appplication wrote: post #75
famouswaffles wrote: post #60

Earlier quoted context omitted.

Recall isn't naturally bidirectional, even for humans. If you are learning vocabulary in a new language, it's common advice to practice both target > source and source > target. Doing only one-way often makes you much better recalling that single direction than both.

I would need further convincing that humans do not naturally tend towards bidirectional recall. Perhaps I’m just on alert anytime I see an LLM-ism that’s met with a claim that the same or similar phenomena holds true in humans as well.

'Naturally' might not be the best word? Maybe 'Necessarily' would be better?

Regardless, it's something that happens in people. Have you not or seen someone else struggle to recall a specific fact or memory until phrased or induced in a certain way?

You probably could also say LLMs 'tend towards bidirectional recall' over the course of training as things that ought to be recalled both ways are reinforced to do so. In the above example, you will also eventually learn both ways with enough exposure even without explicit practice.

Re: A global workspace in language models

#79

Post by _jackdk_ »

kgeist wrote: post #57
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…

Probably an instance of: "The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A" https://arxiv.org/abs/2309.12288

This is also something to be aware of when teaching people, too. I've seen advice for designing Anki-style flashcard decks that reminds people to create flashcards for both A->B and B->A.

Re: A global workspace in language models

#80

Post by unleaded »

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!

What does it say to the second question? I've found Claude is one of the worst models with regards to pop culture knowledge like this, even compared to the Chinese open ones. Just curious, not really relevant to the initial post but I don't pay for it so I only have access to Sonnet.

https://claude.ai/share/5e7e09b2-a75a-4024-b261-9a1a4e063a8b this is mostly hilariously wrong. wrong tie colors, they did not replace their bassist with a drummer, two completely made up albums, the rob cantor song it is thinking of is "shia labeouf", and a few fan behaviours i think it just made up

Post reply on HN