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

Claude's Cycles [pdf]

www-cs-faculty.stanford.edu

Post reply on HN
Print view View original

371–376 of 376 posts

Re: Claude's Cycles [pdf]

#371

Post by whattheheckheck »

igravious wrote: post #308
buffalobuffalo wrote: post #182

Earlier quoted context omitted.

While not on the same level as these guys, I've done some similar stuff using Claude. This is a classic synergy example, where the output of human + LLM is far greater than just the human or just the LLM working on a problem. My experience has been that the LLM lacks fine grained judgement when it comes to allocating resources, or choosing a direction to work in. But once a direction is pointed out, it can do a deep…

> But with someone holding the leash i've been thinking about why we call them agent harnesses i know all analogies suck in different ways but here goes: coding agents are like horses. without a harness and bridle they'll the horse will do as it pleases -- a human can't travel very far and fast by foot but put a bridle and a harness on a horse, give it a bit of coaxing with carrot and stick, add in a bit a pointing t…

Does feel like a mecha suit

Re: Claude's Cycles [pdf]

#372

Post by qsera »

throw310822 wrote: post #370
qsera wrote: post #367

Earlier quoted context omitted.

If someone ask "Hey how do I do this thing in python programming language" what are the chances that you will try to make up a solution, if you have never tried to learn Python? Just tell me..

Have you tried this with Claude? --- Q: How do I reverse an array in the Navajo programming language? A: I'm not familiar with a programming language called "Navajo." It's possible you might be thinking of a different language, or it could be something very niche that I don't have information about. --- As for your question, the chances go from 0 to 100% depending on how many languages I already know and whether I ha…

Lookup how these "fixes" are implemented and please go back and read my original comment.

Re: Claude's Cycles [pdf]

#373

Post by mikeaskew4 »

Claude repeatedly insisted I give up on parsing a relatively vague object recently. When I got more specific, and pressed it to continue, not only did it work, but Claude seemed amazed. Ugh.

Re: Claude's Cycles [pdf]

#374

Post by marcus_holmes »

bitexploder wrote: post #365
marcus_holmes wrote: post #362

Earlier quoted context omitted.

Good points, interesting. I think this is probably neuroscience vs psychology. We can explain a lot with neuroscience, but two people with essentially identical brain chemistry can have very different psychology. There are people out there who have beliefs and cognition processes that I find completely incomprehensible despite having the same brain and even sharing a language. I'm not sure how I'd have a meaningful c…

But at some level, you can "just be" with the other organism. Eat some food. Make some dopamine. Hang out. I feed my dog. I exercise my dog. I exercise myself. I eat. We sit down together, I pet her. We both create oxytocin and perceive that positively when I pet her. Most animals map that to "safety" or "contentment". Survival needs satisfied for now. Who knows what that maps to for my dog, but we exist in a pretty…

Yeah, good point.

I wonder how we would "hang" with an actual AI, though? I guess I'm assuming that it will be a meta-level above the chat and prompts. That's just the ocean it swims in, not it's actual consciousness.

Re: Claude's Cycles [pdf]

#375

Post by littlestymaar »

suddenlybananas wrote: post #247
littlestymaar wrote: post #243

Earlier quoted context omitted.

For what we know, most AI labs have used a majority of artificially data since 2023. I had a discussion about a year ago with a researcher at Kyutai and they told me their lab was spending an order of magnitude more compute in artificial data generation than what they spent in training proper. I can't tell if that ratio applies to the industry as a whole, but artificial datasets are the cornerstone of modern AI train…

I find this very surprising, do you have any papers on the kinds of techniques that they use?

The most well know early paper is probably Textbooks are all you need.

The latest paper from HF on synthetic datasets is a good starting point I think: https://huggingface.co/spaces/HuggingFaceFW/finephrase

The intro contains a few paper that may interest you as well.

Re: Claude's Cycles [pdf]

#376

Post by littlestymaar »

nhecker wrote: post #162
the_af wrote: post #153

Earlier quoted context omitted.

Could you elaborate?

EDIT: probably not relevant, after re-re-reading the comment in question. Presumably littlestymaar is talking about all the LLM-generated output that's publicly available on the Internet (in various qualities but significant quantity) and there for the scraping.

No, I'm talking about generating data for the purpose of training. The latest HF paper on the subject offers a great intro to the technique: https://huggingface.co/spaces/HuggingFaceFW/finephrase
Post reply on HN