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

911–920 of 1001 posts

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

#911

Post by MoreEmpathy »

UltraSane wrote: post #270
neom wrote: post #268

I've been using https://chat.deepseek.com/ over My ChatGPT Pro subscription because being able to read the thinking in the way they present it is just much much easier to "debug" - also I can see when it's bending it's reply to something, often softening it or pandering to me - I can just say "I saw in your thinking you should give this type of reply, don't do that". If it stays free and gets better that's going to b…

If you ask it about the Tienanmen Square Massacre its "thought process" is very interesting.

[dead]

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

#912

Post by MoreEmpathy »

emseetech wrote: post #724
BenChoopao wrote: post #585

Earlier quoted context omitted.

I tried the last prompt and it is no longer working. Sorry, that's beyond my current scope. Let’s talk about something else.

Don't use a hosted service. Download the model and run it locally.

I got this response form https://chat.deepseek.com/ using an old trick that used to work with ChatGPT

https://i.imgur.com/NFFJxbO.png

It's very straightforward to circumvent their censor currently. I suspect it wont last.

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

#913

Post by wredcoll »

axegon_ wrote: post #910
margorczynski wrote: post #907

Earlier quoted context omitted.

Well the US big tech models are strongly left-biased as was shown multiple times. It's almost certain an organization or government will try to push their worldview and narrative into the model. That's why open source models are so important - and on this front DeepSeek wins hands down.

I love how people love throwing the word "left" as it means anything. Need I remind you how many times bots were caught on twitter using chatgpt praising putin? Sure, go ahead and call it left if it makes you feel better but I still take the European and American left over the left that is embedded into russia and china - been there, done that, nothing good ever comes out of it and deepseek is here to back me up with…

Some people feel reality has a leftwing bias.

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

#914

Post by whimsicalism »

ekam wrote: post #891
whimsicalism wrote: post #769

Earlier quoted context omitted.

you’re probably running it on ollama. ollama is doing the pretty unethical thing of lying about whether you are running r1, most of the models they have labeled r1 are actually entirely different models

If you’re referring to what I think you’re referring to, those distilled models are from deepseek and not ollama https://github.com/deepseek-ai/DeepSeek-R1

the choice on naming convention is ollama's, DS did not upload to huggingface that way

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

#915

Post by steelframe »

rpastuszak wrote: post #701
steelframe wrote: post #418

Earlier quoted context omitted.

I tried signing up, but it gave me some bullshit "this email domain isn't supported in your region." I guess they insist on a GMail account or something? Regardless I don't even trust US-based LLM products to protect my privacy, let alone China-based. Remember kids: If it's free, you're the product. I'll give it a while longer before I can run something competitive on my own hardware. I don't mind giving it a few yea…

FWIW it works with Hide my Email, no issues there.

Thanks, but all the same I'm not going to jump through arbitrary hoops set up by people who think it's okay to just capriciously break email. They simply won't ever get me as a customer and/or advocate in the industry. Same thing goes for any business that is hostile toward open systems and standards.

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

#916

Post by ExtraEmpathy »

Shocka1 wrote: post #899
dutchbookmaker wrote: post #804

Earlier quoted context omitted.

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!"

Something off about this comment and the account it belongs to being 7 days old. Please post the problem/prompt you used so it can be cross checked.

[dead]

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

#917

Post by ExtraEmpathy »

rapsey wrote: post #504
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…

The nVidia market price could also be questionable considering how much cheaper DS is to run.

[dead]

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

#918

Post by margorczynski »

axegon_ wrote: post #910
margorczynski wrote: post #907

Earlier quoted context omitted.

Well the US big tech models are strongly left-biased as was shown multiple times. It's almost certain an organization or government will try to push their worldview and narrative into the model. That's why open source models are so important - and on this front DeepSeek wins hands down.

I love how people love throwing the word "left" as it means anything. Need I remind you how many times bots were caught on twitter using chatgpt praising putin? Sure, go ahead and call it left if it makes you feel better but I still take the European and American left over the left that is embedded into russia and china - been there, done that, nothing good ever comes out of it and deepseek is here to back me up with…

Seriously, pro-Putin Twitter bots is the argument against open source LLMs from China?

If you re-read what I've wrote (especially the last line) you'll understand that I don't have to accept what the left/right of USA/Europe or China/Russia thinks or wants me to think - the model is open source. That's the key point.

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

#919

Post by SecretDreams »

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…

Totally agreed.
Post reply on HN