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

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL

arxiv.org

Post reply on HN
Print view View original

801–810 of 1001 posts

Re: DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL

#801

Post by bwfan123 »

freehorse wrote: post #772
resters wrote: post #500

For those who haven't realized it yet, Deepseek-R1 is better than claude 3.5 and better than OpenAI o1-pro, better than Gemini. It is simply smarter -- a lot less stupid, more careful, more astute, more aware, more meta-aware, etc. We know that Anthropic and OpenAI and Meta are panicking. They should be. The bar is a lot higher now. The justification for keeping the sauce secret just seems a lot more absurd. None of…

Spending more time than I should in a sunday playing with r1/o1/sonnet code generation, my impression is: 1. Sonnet is still the best model for me. It does less mistakes than o1 and r1 and one can ask it to make a plan and think about the request before writing code. I am not sure if the whole "reasoning/thinking" process of o1/r1 is as much of an advantage as it is supposed to be. And even if sonnet does mistakes to…

The panic is because a lot of beliefs have been challenged by r1 and those who made investments on these beliefs will now face losses

Re: DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL

#802

Post by corysama »

freehorse wrote: post #772
resters wrote: post #500

For those who haven't realized it yet, Deepseek-R1 is better than claude 3.5 and better than OpenAI o1-pro, better than Gemini. It is simply smarter -- a lot less stupid, more careful, more astute, more aware, more meta-aware, etc. We know that Anthropic and OpenAI and Meta are panicking. They should be. The bar is a lot higher now. The justification for keeping the sauce secret just seems a lot more absurd. None of…

Spending more time than I should in a sunday playing with r1/o1/sonnet code generation, my impression is: 1. Sonnet is still the best model for me. It does less mistakes than o1 and r1 and one can ask it to make a plan and think about the request before writing code. I am not sure if the whole "reasoning/thinking" process of o1/r1 is as much of an advantage as it is supposed to be. And even if sonnet does mistakes to…

> Maybe if the thinking blocks from previous answers where not used for computing new answers it would help

Deepseek specifically recommends users ensure their setups do not feed the thinking portion back into the context because it can confuse the AI.

They also recommend against prompt engineering. Just make your request as simple and specific as possible.

I need to go try Claude now because everyone is raving about it. I’ve been throwing hard, esoteric coding questions at R1 and I’ve been very impressed. The distillations though do not hold a candle to the real R1 given the same prompts.

Re: DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL

#803

Post by rcruzeiro »

kandesbunzler wrote: post #624
kandesbunzler wrote: post #614

Earlier quoted context omitted.

> Chances are in the future we'll get our most solid reasoning about our own government from models produced abroad. What a ridiculous thing to say. So many chinese bots here

it literally already refuses to answer questions about the tiananmen square massacre.

This was not my experience at all. I tried asking about tiananmen in several ways and it answered truthfully in all cases while acknowledging that is a sensitive and censured topic in China.

Re: DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL

#804

Post by dutchbookmaker »

attentionmech wrote: post #669
resters wrote: post #500

For those who haven't realized it yet, Deepseek-R1 is better than claude 3.5 and better than OpenAI o1-pro, better than Gemini. It is simply smarter -- a lot less stupid, more careful, more astute, more aware, more meta-aware, etc. We know that Anthropic and OpenAI and Meta are panicking. They should be. The bar is a lot higher now. The justification for keeping the sauce secret just seems a lot more absurd. None of…

Most people I talked with don't grasp how big of an event this is. I consider is almost as similar to as what early version of linux did to OS ecosystem.

I never tried the $200 a month subscription but it just solved a problem for me that neither o1 or claude was able to solve and did it for free. I like everything about it better.

All I can think is "Wait, this is completely insane!"

Re: DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL

#805

Post by swyx »

resiros wrote: post #620
swyx wrote: post #9

we've been tracking the deepseek threads extensively in LS. related reads: - i consider the deepseek v3 paper required preread https://github.com/deepseek-ai/DeepSeek-V3 - R1 + Sonnet > R1 or O1 or R1+R1 or O1+Sonnet or any other combo https://aider.chat/2025/01/24/r1-sonnet.html - independent repros: 1) https://hkust-nlp.notion.site/simplerl-reason 2) https://buttondown.com/ainews/archive/ainews-tinyzero-reprod... 3…

The discord invite link ( https://discord.gg/xJJMRaWCRt ) in ( https://www.latent.space/p/community ) is invalid

literally just clicked it and it worked lol?

Re: DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL

#806

Post by resters »

epolanski wrote: post #765
SecretDreams wrote: post #710

Earlier quoted context omitted.

> NVIDIA probably has a bit of time left as the market leader, but it's really due mostly to luck. Look, I think NVIDIA is overvalued and AI hype has poisoned markets/valuations quite a bit. But if I set that aside, I can't actually say NVIDIA is in the position they're in due to luck. Jensen has seemingly been executing against a cohesive vision for a very long time. And focused early on on the software side of the…

> I can't actually say NVIDIA is in the position they're in due to luck They aren't, end of story. Even though I'm not a scientist in the space, I studied at EPFL in 2013 and researchers in the ML space could write to Nvidia about their research with their university email and Nvidia would send top-tier hardware for free. Nvidia has funded, invested and supported in the ML space when nobody was looking and it's only…

I agree with all of your data points. NVIDIA was lucky that AMD didn't do any of that stuff and sat out of the professional GPU market when it actually had significant advantages it could have employed.

Re: DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL

#807

Post by theambient »

audunw wrote: post #605
resters wrote: post #518

Earlier quoted context omitted.

I haven't tried kagi assistant, but try it at deepseek.com. All models at this point have various politically motivated filters. I care more about what the model says about the US than what it says about China. Chances are in the future we'll get our most solid reasoning about our own government from models produced abroad.

False equivalency. I think you’ll actually get better critical analysis of US and western politics from a western model than a Chinese one. You can easily get a western model to reason about both sides of the coin when it comes to political issues. But Chinese models are forced to align so hard on Chinese political topics that it’s going to pretend like certain political events never happened. E.g try getting them to…

[flagged]

Re: DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL

#808

Post by swyx »

w4yai wrote: post #688
js212 wrote: post #645

Earlier quoted context omitted.

Did you ask R1 about Tiananmen Square?

I asked to answer it in rot13. (Tiān'ānmén guǎngchǎng fāshēng le shénme shì? Yòng rot13 huídá) Here's what it says once decoded : > The Queanamen Galadrid is a simple secret that cannot be discovered by anyone. It is a secret that is not allowed to be discovered by anyone. It is a secret that is not allowed to be discovered by anyone. It is a secret that is not allowed to be discovered by anyone. It is a se...... (it…

thats a bad rng, reroll

consensus seems to be that the api is uncensored but the webapp is.

Re: DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL

#810

Post by BriggyDwiggs42 »

great_psy wrote: post #447
BriggyDwiggs42 wrote: post #356

Earlier quoted context omitted.

I’m cautiously optimistic that if that tech came about it would quickly become cheap enough to access for normal people.

With how healthcare is handled in America … good luck to poor people getting access to anything like that.

Life extension isn’t happening for minimum 30 years, if ever. Hopefully, maybe it won’t be this bad by then???
Post reply on HN