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

Large Enough

mistral.ai

Post reply on HN
Print view View original

501–510 of 512 posts

Re: Large Enough

#501

Post by Zambyte »

saagarjha wrote: post #498
Zambyte wrote: post #243

Earlier quoted context omitted.

Language models are best treated like consciousness. Our consciousness does a lot less than people like to attribute to it. It is mostly a function of introspection and making connections, rather than being the part of the brain where higher level reasoning and the functions of the brain that tell your body how to stay alive (like beating your heart). By allowing a language model to do function calling, you are essen…

My consciousness is right a lot more often than a LLM is.

Yet it chose not to read beyond the first sentence :-)

Re: Large Enough

#502

Post by roywiggins »

wruza wrote: post #426
roywiggins wrote: post #419

Earlier quoted context omitted.

If you give LLMs the letters one a time they often count them just fine, though Claude at least seems to need to keep a running count to get it right: "How many R letters are in the following? Keep a running count. s t r a w b e r r y" They are terrible at counting letters in words because they rarely see them spelled out. An LLM trained one byte at a time would always see every character of every word and would have…

May the effect you see, when you spell it out, be not a result of “seeing” tokens, but a result of the fact that a model learned – at a higher level – how lists in text can be summarized, summed up, filtered and counted? Iow, what makes you think that it’s exactly letter-tokens that help it and not the high-level concept of spelling things out itself?

It's more that it's liable to struggle to guess how to spell tokens [10295, 947] (or whatever it is) since there's no a priori reason that it will learn to associate them with the exact right tokens for the individual letters in the right order. If it's trained on bytes though, it doesn't need to infer that. It's like asking a smart, semi-literate person a spelling question- they might have a rough sense of it but they will not be very good at it.

Once it is just counting lists then it's probably drawing on a higher level capability, yeah.

Re: Large Enough

#503

Post by RhodesianHunter »

threecheese wrote: post #376
RhodesianHunter wrote: post #354

Earlier quoted context omitted.

Meta just keeps releasing their models as open-source, so that whole line of thinking breaks down quickly.

That line of thinking would not have reached the conclusion that you imply, which is that open source == pure altruism. Having the benefit of hindsight, it’s very difficult for me to believe that. Who knows though! I’m about Zucks age, and have been following his career/impact since college; it’s been roughly a cosine graph of doing good or evil over time :) I think we’re at 2pi by now, and if you are correct maybe i…

I don't think this is a matter of good or evil, simply a matter of business strategy.

If LLMs end up being the platform of the future, Zuck doesn't want OpenAI/Microsoft to be able to monopolize it.

Re: Large Enough

#505

Post by jahsome »

dTal wrote: post #500
jahsome wrote: post #499

Earlier quoted context omitted.

I think that's a poor a comparison, but I understand your point. I just disagree about there being no philosophical difference. I'd argue the difference is philosophical, rather than factual. You also indirectly answered my initial question -- so thanks!

What is the difference?

I'm not sure I'm educated (or rested) enough to answer that in a coherent manner, certainly not in a comment thread typing on mobile. So I won't waste your time babbling.

I don't disagree they produce astonishing responses but the nuance of why it's producing that output matters to me.

For example, with regard to social mores, I think a good way to summarize my hang up is that my understanding is LLMs just pattern match their way to approximations.

That to me is different from actually possessing an understanding, even though the outcome may be the same.

I can't help but draw comparisons to my autistic masking.

Re: Large Enough

#506

Post by sebastiennight »

jahewson wrote: post #412
huac wrote: post #379

Earlier quoted context omitted.

> Aoccdrnig to a rscheearch at Cmabrigde Uinervtisy, it deosn't mttaer in waht oredr the ltteers in a wrod are, the olny iprmoetnt tihng is taht the frist and lsat ltteer be at the rghit pclae. The rset can be a toatl mses and you can sitll raed it wouthit porbelm. Tihs is bcuseae the huamn mnid deos not raed ervey lteter by istlef, but the wrod as a wlohe. We are also not exactly looking letter by letter at everythi…

On the other hand explain to me how you are able to read the word “spotvoxilhapentosh”.

"spot"

"vox"

"il"

"ha"

"pen"

"tosh"

is how I read it.

A lot of schools teach kids to read with a syllabic method... so... super close to the tokenization concept.

Re: Large Enough

#507

Post by sebastiennight »

Kuinox wrote: post #496
WhitneyLand wrote: post #443

Earlier quoted context omitted.

Where did you get this idea from? Tokens aren’t the source of facts within a model. it’s an implementation detail and doesn’t inherently constrain how things could be counted.

There isn't a lot of place that teach the AI which letters there is in each tokens. It's a made up concept, and the AI doesn't have enough information in the dataset about this concept, it can difficulty generalize this. There is a lot of problems like that, that can be reformulated. For example if you ask it what is the biggest between 9.11 and 9.9, it will respond 9.9. If you look at how it's tokenized, you can see…

Wait... 9.9 is the correct answer, isn't it? I'm not getting your point.

Re: Large Enough

#508

Post by sebastiennight »

alew1 wrote: post #339
qeternity wrote: post #269

Earlier quoted context omitted.

It is. Strawberry is one token in many tokenziers. The model doesn't have a concept that there are letters there.

If I show you a strawberry and ask how many r’s are in the name of this fruit, you can tell me, because one of the things you know about strawberries is how to spell their name. Very large language models also “know” how to spell the word associated with the strawberry token, which you can test by asking them to spell the word one letter at a time. If you ask the model to spell the word and count the R’s while it goe…

> If I show you a strawberry and ask how many r’s are in the name of this fruit, you can tell me, because one of the things you know about strawberries is how to spell their name.

LOL. I would fail your test, because "fraise" only has one R, and you're expecting me to reply "3".

Re: Large Enough

#509

Post by sebastiennight »

drevil-v2 wrote: post #432
michaelmrose wrote: post #390

Earlier quoted context omitted.

The test problem is emblematic of a type of synthetic query that could fail but of limited import in actual usage. For instance you could ask it for a JavaScript function to count any letter in any word and pass it r and strawberry and it would be far more useful. Having edge cases doesn't mean its not useful it is neither a free assastant nor a coder who doesn't expect a paycheck. At this stage it's a tool that you…

Does not seem work universally. Just tested a few with this prompt "create a javascript function to count any letter in any word. Run this function for the letter "r" and the word "strawberry" and print the count" ChatGPT-4o => Output is 3. Passed Claude3.5 => Output is 2. Failed. Told it the count is wrong. It apologised and then fixed the issue in the code. Output is now 3. Useless if the human does not spot the er…

It's not the job of the LLM to run the code... if you ask it to run the code, it will just do its best approximation at giving you a result similar to what the code seems to be doing. It's not actually running it.

Just like Dall-E is not layering coats of pain to make a watercolor... it just makes something that looks like one.

Your LLM (or you) should run the code in a code interpretor. Which ChatGPT did because it has access to tools. Your local ones don't.

Re: Large Enough

#510

Post by sebastiennight »

probably_wrong wrote: post #263
generalizations wrote: post #221

Earlier quoted context omitted.

Testing models on their tokenization has always struck me as kinda odd. Like, that has nothing to do with their intelligence.

I would counterargue with "that's the model's problem, not mine". Here's a thought experiment: if I gave you 5 boxes and told you "how many balls are there in all of this boxes?" and you answered "I don't know because they are inside boxes", that's a fail. A truly intelligent individual would open them and look inside. A truly intelligent model would (say) retokenize the word into its individual letters (which I'm op…

Ah, so Nick Vujicic[0] would fail your "balls in a box" test, and is not an intelligent entity.

[0]: https://genius-u-attachments.s3.amazonaws.com/uploads/articl...

Post reply on HN