Ask HN: Any insider takes on Yann LeCun's push against current architectures?

Post by chongli » Sat, Mar 15, 2025, 6:04 AM UTC

csomar wrote: post #213

ThinkBeat wrote: post #146

Earlier quoted context omitted.

No. > The sun feels hot on your skin. No matter how many times you read that, you cannot understand what the experience is like. > You can read a book about Yoga and read about the Tittibhasana pose But by just reading you will not understand what it feels like. And unless you are in great shape and with greate balance you will fail for a while before you get it right. (which is only human). I have read what shooting…

All of these "experiences" are encoded in your brain as electricity. So "text" can encode them, though English words might not be the proper way to do it.

Post by golergka » Sat, Mar 15, 2025, 6:21 AM UTC

ThinkBeat wrote: post #146

codenlearn wrote: post #138

Earlier quoted context omitted.

Doesn't Language itself encode multimodal experiences? Let's take this case write when we write text, we have the skill and opportunity to encode the visual, tactile, and other sensory experiences into words. and the fact is llm's trained on massive text corpora are indirectly learning from human multimodal experiences translated into language. This might be less direct than firsthand sensory experience, but potentia…

No. > The sun feels hot on your skin. No matter how many times you read that, you cannot understand what the experience is like. > You can read a book about Yoga and read about the Tittibhasana pose But by just reading you will not understand what it feels like. And unless you are in great shape and with greate balance you will fail for a while before you get it right. (which is only human). I have read what shooting…

Post by the_arun » Sat, Mar 15, 2025, 6:49 AM UTC

csomar wrote: post #213

ThinkBeat wrote: post #146

Earlier quoted context omitted.

No. > The sun feels hot on your skin. No matter how many times you read that, you cannot understand what the experience is like. > You can read a book about Yoga and read about the Tittibhasana pose But by just reading you will not understand what it feels like. And unless you are in great shape and with greate balance you will fail for a while before you get it right. (which is only human). I have read what shooting…

All of these "experiences" are encoded in your brain as electricity. So "text" can encode them, though English words might not be the proper way to do it.

Post by wavemode » Sat, Mar 15, 2025, 7:02 AM UTC

QuesnayJr wrote: post #222

wavemode wrote: post #219

Earlier quoted context omitted.

I tried this just now on Chatbot Arena, and both chatbots very confidently got the name of the park wrong. Perhaps you thought I meant "1st and 2nd" literally? I was just using those as an example so I don't reveal where I live. You should use actual street names that are near a public park, and you can feel free to specify the city and state.

I did think you meant it literally. Since I can't replicate the question you asked, I have no way of verifying your claim.

Post by randomNumber7 » Sat, Mar 15, 2025, 7:38 AM UTC

eximius wrote: post #95

I believe that so long as weights are fixed at inference time, we'll be at a dead end. Will Titans be sufficiently "neuroplastic" to escape that? Maybe, I'm not sure. Ultimately, I think an architecture around "looping" where the model outputs are both some form of "self update" and "optional actionality" such that interacting with the model is more "sampling from a thought space" will be required.