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

DeepSeek v4

api-docs.deepseek.com

Post reply on HN
Print view View original

561–570 of 1001 posts

Re: DeepSeek v4

#561

Post by iso1631 »

cde-v wrote: post #518
sigmoid10 wrote: post #332

Earlier quoted context omitted.

Still not sure how I feel about China of all places to control the only alternative AI stack, but I guess it's better than leaving everything to the US alone. If China ever feels emboldened enough to go for Taiwan and the US descends into complete chaos, the rest of the world running on AI will be at the mercy of authoritarian regimes. At the very least you can be sure noone is in this for the good of the people anym…

China doesn't even care about Taiwan anymore, their saber-rattling about it is a convenient distraction while they quietly make it completely irrelevant in the next few years.

It does seem the idea is to get the Taiwanese people to want to choose to rejoin China by making China far better for people to live than Taiwan. Maybe that will be via democracy (i.e. China manipulates the people of Taiwan), or perhaps it will be genuine (i.e. China provides a far better lifestyle for the average person than Taiwan)

Re: DeepSeek v4

#562

Post by anentropic »

cmrdporcupine wrote: post #551
amunozo wrote: post #275

For those who rely on open source models but don't want to stop using frontier models, how do you manage it? Do you pay any of the Chinese subscription plans? Do you pay the API directly? After GPT 5.5 release, however good it is, I am a bit tired of this price hiking and reduced quota every week. I am now unemployed and cannot afford more expensive plans for the moment.

For DeepSeek you can use their API and if you ran it constantly you'd still be under what OpenAI or Anthropic charge for a coding plan.

I had Claude make me a quick tool to combine my Claude Code token usage (via ccusage util) with OpenRouter pricing from the models API

I'm on Max x5 plan and any of the 'good' models like Kimi 2.6, GLM, DeepSeek would have cost 3-5x in per-token billing for what I used on my Claude plan the last three months

So unless my Claude fudged the maths to make itself look better, seems like I'm getting a good deal

Re: DeepSeek v4

#563

Post by taytus »

nsoonhui wrote: post #542
jari_mustonen wrote: post #239

Open Source as it gets in this space, top notch developer documentation, and prices insanely low, while delivering frontier model capabilities. So basically, this is from hackers to hackers. Loving it! Also, note that there's zero CUDA dependency. It runs entirely on Huawei chips. In other words, Chinese ecosystem has delivered a complete AI stack. Like it or not, that's a big news. But what's there not to like when…

Sorry, but exactly where did you get the idea that DS V4 runs entirely on Huawei? I asked DS itself and it denied this. It says: 'Nvidia chips are absolutely used for DeepSeek V4. The reality is a pragmatic "both-and" strategy, not an "either-or."' And based on the DS V4 technical report ( https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main... ), it is mentioned that: We validated the fine-grained EP scheme…

>I asked DS itself and it denied this

Bro, seriously?

Re: DeepSeek v4

#564

Post by 2ndorderthought »

rhubarbtree wrote: post #393
sudo_cowsay wrote: post #292

Earlier quoted context omitted.

I sometimes wonder if there are any security risks with using Chinese LLMs. Is there?

Backdooring software at scale. Spearphishing. Building reliance and exploiting it, through state subsidies, dumping, and market manipulation. Handicapping provision to the west for competitive advantage.

Do you think doing any of those things with in the next year does more to forward China as a super power then say, dethroning all of the US hype around LLMs?

Tech ceos are going around talking about how they will rule over employees and they will be unable to work in the future except for intelligence tokens. What if China commoditizes that without spending nearly as much resources? Kind of makes the trillions of dollars invested in the US a literal joke.

Re: DeepSeek v4

#565

Post by cztomsik »

hodgehog11 wrote: post #282
cztomsik wrote: post #277

So is this the first AI lab using MUON for their frontier model?

No, Muon was developed by Moonshot; they've been using it in their Kimi models since Kimi K2 in 2025.

Jordan Keller worked at Moonshot? Or am I missing something? I thought he is the original author. https://x.com/kellerjordan0/status/1842300916864844014

Re: DeepSeek v4

#566

Post by anentropic »

madagang wrote: post #39
doctoboggan wrote: post #21

Earlier quoted context omitted.

Is it honestly better than Opus 4.6 or just benchmaxxed? Have you done any coding with an agent harness using it? If its coding abilities are better than Claude Code with Opus 4.6 then I will definitely be switching to this model.

Their Chinese announcement says that, based on internal employee testing, it is not as good as Opus 4.6 Thinking, but is slightly better than Opus 4.6 without Thinking enabled.

Who uses Opus without thinking though...?

Re: DeepSeek v4

#568

Post by naveen99 »

hunter67 wrote: post #357
raincole wrote: post #250

Earlier quoted context omitted.

[flagged]

Our (western) economic model forces competing individual companies to be profitable quickly. China can ignore DeepSeek losing money, because they know developing DeepSeek will help China. Not every institution needs to be profitable.

You mean like intel, tesla, spacex, openai ?

Re: DeepSeek v4

#569

Post by 2ndorderthought »

Bombthecat wrote: post #291
schneehertz wrote: post #201

Earlier quoted context omitted.

This price is high even because of the current shortage of inference cards available to DeepSeek; they claimed in their press release that once the Ascend 950 computing cards are launched in the second half of the year, the price of the Pro version will drop significantly

In six month deepseek won't be sota anymore und usage will be wayyyy down.

A huge proportion of those scores are gamed anyways. Use whatever works for you at the price and availability you can afford

Re: DeepSeek v4

#570

Post by yanis_t »

Assuming it is almost as good as Opus 4.6 (which benchmarks seem to give evidence for), and assuming we are having a good enough harness (PI, OpenCode), it's is now more than 5x cheaper.

I just want to remind you that this is happening at the same time as Anthropic A/B tests removal of Code from Pro Plan, and as OpenAI releases gpt-5.5 2x more expensive than gpt-5.4...

Post reply on HN