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

An analysis of DeepSeek's R1-Zero and R1

arcprize.org

Post reply on HN
Print view View original

101–110 of 280 posts

Re: An analysis of DeepSeek's R1-Zero and R1

#101

Post by Uehreka »

aprilthird2021 wrote: post #87
Uehreka wrote: post #75

Earlier quoted context omitted.

This assumes that the companies gathering the data don’t have silent ways of detecting bad actors and discarding their responses. If you’re trying to poison an AI, are you making all of your queries from the same IP? Via a VPN whose IP block is known? Are you using a tool to generate this bad data, which might have detectable word frequency patterns that can be detected with something cheap like tf-idf? There’s a lot…

> If you’re trying to poison an AI, are you making all of your queries from the same IP? Via a VPN whose IP block is known? We can use the same tactics they are using to crawl the web and scrape pages and bypass anti-scraping mechanisms.

Not necessarily, not all tactics can be used symmetrically like that. Many of the sites they scrape feel the need to support search engine crawlers and RSS crawlers, but OpenAI feels no such need to grant automated anonymous access to ChatGPT users.

And at the end of the daty, they can always look at the responses coming in and make decisions like “95% of users said these responses were wrong, 5% said these responses were right, let’s go with the 95%”. As long as the vast majority of their data is good (and it will be) they have a lot of statistical tools they can use to weed out the poison.

Re: An analysis of DeepSeek's R1-Zero and R1

#102

Post by levocardia »

dagelf wrote: post #2

Well o3 scored 75% on AGI-1, R1 and o1 only 25%.... watch this space though....

What's interesting is that you can already see the "AI race" dynamics in play -- OpenAI must be under immense market pressure to push o3 out to the public to reclaim "king of the hill" status.

Re: An analysis of DeepSeek's R1-Zero and R1

#103

Post by victorbjorklund »

jl6 wrote: post #67
sheepdestroyer wrote: post #21

Earlier quoted context omitted.

From the article : o3 (low) 75.7% 335K $20 o3 (high) 87.5% 57M $3.4K

$3.4K is about what you might pay a magic circle lawyer for an opinion on a matter. Not saying o3 is an efficient use of resources, just saying that it’s not outlandish that a sufficiently good AI could be worth that kind of money.

You pay that price to a law firm to get good service and to get a "guarantee" of correctness. You get neither from an LLM. Not saying it is not worth anything but you cant compare it to a top law firm.

Re: An analysis of DeepSeek's R1-Zero and R1

#104

Post by genewitch »

aprilthird2021 wrote: post #45
polishdude20 wrote: post #6

I predict that the future of LLM's when it comes to coding and software creation is in "custom individually tailored apps". Imagine telling an AI agent what app you want, the requirements and all that and it just builds everything needed from backend to frontend, asks for your input on how things should work, clarifying questions etc. It tests the software by compiling and running it reading errors and failed tests a…

> auto run your code, compile it, feed errors back to the LLM, Can't wait for companies to juice profits by having the LLM run excessive cycles or get stuck in a loop and run up my bill

aider jams the backend on my PC, i have to kill the tcp connection or python to stop it running a GPU on the backend, from time to time. I can't imagine paying for tokens and not knowing if it's working or wasting money.

Re: An analysis of DeepSeek's R1-Zero and R1

#105

Post by svdr »

dr_dshiv wrote: post #68

> The R1-Zero training process is capable of creating its own internal domain specific language (“DSL”) in token space via RL optimization. Um, what’s that now? Really?

Yeah, if I understand correctly AI will create it's own internal reasoning language through RL. In R1-Zero it was already a strange mix of languages. They corrected that for R1 to make the thinking useful for humans.

Re: An analysis of DeepSeek's R1-Zero and R1

#106

Post by blibble »

BorisMelnik wrote: post #60
nine_k wrote: post #46

Earlier quoted context omitted.

This assumes that you give honest feedback. Efforts to feed deployed AI models various epistemic poisons abound in the wild.

I am not in this space, question: are there "bad actors" that are known to feed AI models with poisonous information?

yes, example: me

I more often than not use the thumbs up on bad Google AI answers

(but not always! can't find me that easily!)

Re: An analysis of DeepSeek's R1-Zero and R1

#107

Post by Davidzheng »

aithrowawaycomm wrote: post #64
anothermathbozo wrote: post #3

The claim is that this removes the human bottleneck (aka SFT or supervised fine tuning) on domains with a verifiable reward. Critically, this verifiable reward is extremely hard to pin down in nearly all domains besides mathematics and computer science.

It's also extremely hard to nail down in much of mathematics or computer science! - is such-and-such theorem deep or shallow? - is this definition/axiom useful? (there's a big difference between doing compass-straightedge proofs vs. wondering about the parallel postulate) - more generally, discovering theorems is generally not amenable to verifiable rewards, except in domains where simpler deterministic tools exist (…

Not clear to me that theorem discovery is not amenable to verifiable rewards. I think most important theorems probably are recovered automatically by asking AI systems to proof increasing complicated human conjectures. Along the way I expect emergent behaviors of creating conjectures and recognizing important self-breakthroughs. Much like regret emergence

Re: An analysis of DeepSeek's R1-Zero and R1

#109

Post by talldayo »

mrbungie wrote: post #74
ClumsyPilot wrote: post #47

Earlier quoted context omitted.

I think future of inference is on the client side You can do inference on almost any hardware, I do not see any edge for NVIDIA here I can download DeepSeek 30b model and run inference at good speed on AMD GPU ms and even on CPU. Apple silicon works fine too. I get >50 tokens/s on £300 AMD GPUs. The main bottleneck appears to be memory, not processing power.

In fact, I'm not sure how the "we will need tons of centralized inference infrastructure" argument works when Apple with +50% smartphone market share in the USA has a totally opposite strategy focused on privacy: on-device inference.

Apple's strategy already failed. Their big bet on NPU hardware did not pay off at all, and right now it's effectively wasted silicon on every iDevice while the GPU does all the heavy inference work. Now they partner with OpenAI to handle their inference (and even that's not good enough in many cases[0]). The "centralized compute" lobby is being paid by Apple to do the work their devices cannot.

Until Apple or AMD unifies their GPU architectures and implements complex streaming multiprocessors, Nvidia will remain in a class of their own. Apple used to lead the charge on the foremost CUDA alternative too, but then they abandoned it to focus on proprietary standards instead. It's pretty easy to argue that Apple shot themselves in the foot with every opportunity they had to compete on good faith. And make no mistake: Apple could have competed with Nvidia if they weren't so stubborn about Linux support and putting smartphone GPUs in laptops and desktops.

[0] https://apnews.com/article/apple-ai-news-hallucinations-ipho...

Re: An analysis of DeepSeek's R1-Zero and R1

#110

Post by Davidzheng »

artninja1988 wrote: post #4

>Ultimately, R1-Zero demonstrates the prototype of a potential scaling regime with zero human bottlenecks – even in the training data acquisition itself. I would like this to be true, but doesn't the way they're doing RL also require tons of human data?

I think yes. But hopefully in math with compute advances we can lower the human data input by increasing the gap that is bridged by raw model capabilities vs search augmentation (either with tree search or full rollouts)
Post reply on HN