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

Caveman: Why use many token when few token do trick

github.com

Post reply on HN
Print view View original

391–396 of 396 posts

Re: Caveman: Why use many token when few token do trick

#391

Post by K0balt »

qsera wrote: post #375
K0balt wrote: post #322

Earlier quoted context omitted.

Except I actually mean to infer the concept of adding things from examples. LLMs are amply capable of applying concepts to data that matches patterns not ever expressed in the training data. It’s called inference for a reason. Anthropomorphic descriptions are the most expressive because of the fact that LLMs based on human cultural output mimic human behaviours, intrinsically. Other terminology is not nearly as expre…

>do manage to effectively convey the external effect But the problem is that this does not inform about the failure mode. So if I am understanding correctly, you are saying that the behavior of LLM, when it works, is like it has internalized the concepts. But then it does not inform that it can also say stuff that completely contradicts what it said before, there by also contradicting the notion of having "internaliz…

You never met a person that isn’t always right or one that makes up shit to sound smart? Because that’s the pattern you are describing that is being matched.

Re: Caveman: Why use many token when few token do trick

#392

Post by dostick »

adam_patarino wrote: post #389
dostick wrote: post #388

Earlier quoted context omitted.

I only understood half of the tech jargon in your answer. If I understood it all I’d probably run it myself. If someone who is less knowing than me is your customer, you need to explain in simpler terms!

Fair enough! The simple answer is: we did a lot of work to make the model better at coding without requiring complicated installation or configuration. One comman to install and run. All the benefits of claude code, without any of the limitations or rug pulls.

I’m not nitpicking, but you’re saying better than Claude or Codex? Is it also focused and tested mainly on web/JS technologies? It’s still berry much uphill battle building native apps. I think there’s untapped market for Swift / Android coding models.

Re: Caveman: Why use many token when few token do trick

#393

Post by adam_patarino »

dostick wrote: post #392
adam_patarino wrote: post #389

Earlier quoted context omitted.

Fair enough! The simple answer is: we did a lot of work to make the model better at coding without requiring complicated installation or configuration. One comman to install and run. All the benefits of claude code, without any of the limitations or rug pulls.

I’m not nitpicking, but you’re saying better than Claude or Codex? Is it also focused and tested mainly on web/JS technologies? It’s still berry much uphill battle building native apps. I think there’s untapped market for Swift / Android coding models.

Actually, we're more broadly trained than most models. We did long tail training across languages, so we improved execution with languages like java, swift, and even cobol.

It's definitely a david vs goliath. But we know there's a subset of devs who need the privacy or unlimited nature of local.

Re: Caveman: Why use many token when few token do trick

#394

Post by larodi »

weird-eye-issue wrote: post #358
larodi wrote: post #318

Earlier quoted context omitted.

this continual down-voting is not a personal thing for sure. perhaps there are crawlers that pretend to be more humane, or fully automated llm commenters which also randomly downvote.

Instead of conspiracy theories don't you think it's just likely that it was people downvoting a stupid comment?

Stick around and you’ll find out. And, no, it is even statistically unlikely some leaf comments ever get that much attention.

Re: Caveman: Why use many token when few token do trick

#396

Post by Perz1val »

dalmo3 wrote: post #325
Perz1val wrote: post #171

Earlier quoted context omitted.

I think good, less thinking for you, more thinking you will do

I'm not sure if you're being sarcastic or not, but I did find the caveman examples harder to read than their verbose counterpart. The verbose ones I could speed read, and consume it at a familiar pace... Almost on autopilot. Caveman speak no familiar no convention, me no know first time. Need think hard understand. Slower. Good thing?

That was my point. You (and I) tend to read verobose text and not argue with it, our brains are spoonfed reasoning chains and they seem to make sense. Caveman breaks that, so we have to actually think, there is no "thinking" done for us
Post reply on HN