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

721–730 of 1001 posts

Re: DeepSeek v4

#721

Post by embedding-shape »

mchusma wrote: post #718

At first, I was more excited about the Flash model, but I'm now more excited about the Pro model in many ways. I feel like the Pro model with an Run through unsloth, and with some fine tuning, is gonna be enough for many vertical SaaS applications. Where previously I was wary to under-provide the intelligence level, I'm now more excited about the idea of being able to give these pretty large intelligent models to my…

> The idea that for basically sub-agents, we can fine-tune them, should reasonably expect to perform as well as Opus for a specific subtask of which my applications have many [...] we can run a general-purpose intelligent model, Sonnet or Opus, orchestrating a fleet of, let's say, 30 to 50 of these sub-agents that have been fine-tuned

I've heard so many people saying this for the last year, and even tried doing it myself too, and never seen a successful application of it, nor succeeded myself either with SOTA models that are smart but slow or local models that are dumb but fast (even with beefy hardware).

What makes you believe this is possible in the first place? Every "swarm of agents" implementation I've seen only been able to produce lowest quality of code, most of the time vastly bloated, but surely you must have seen something working in practice that you could share with the rest of us?

Re: DeepSeek v4

#722

Post by srj »

Ladioss wrote: post #376
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…

I always find it an illuminating experience about the power of mass propaganda every time I see an American believe they somewhat have the moral high ground over China, despite starting a new war somewhere around the globe either for petrol or on behalf of Israel every six months.

On the contrary, I find reading your own confused spin on morality here an interesting window into the effectiveness of propaganda. You're taking two oppressive authoritarian governments and elevating them above the US.

Re: DeepSeek v4

#723

Post by solenoid0937 »

ozgune wrote: post #510
hodgehog11 wrote: post #304

There are quite a few comments here about benchmark and coding performance. I would like to offer some opinions regarding its capacity for mathematics problems in an active research setting. I have a collection of novel probability and statistics problems at the masters and PhD level with varying degrees of feasibility. My test suite involves running these problems through first (often with about 2-6 papers for conte…

I reviewed how DeepSeek V4-Pro, Kimi 2.6, Opus 4.6, and Opus 4.7 across the same AI benchmarks. All results are for Max editions, except for Kimi. Summary: Opus 4.6 forms the baseline all three are trying to beat. DeepSeek V4-Pro roughly matches it across the board, Kimi K2.6 edges it on agentic/coding benchmarks, and Opus 4.7 surpasses it on nearly everything except web search. DeepSeek V4-Pro Max shines in competit…

I feel like people suck at promoting Opus. Baseline, it's pretty on par with GPT 5.5.

But if you prompt it well - give it the reasoning behind why you're asking it to do something - it pulls far ahead.

Re: DeepSeek v4

#724

Post by embedding-shape »

XCSme wrote: post #597

Something is odd with this model, their blog posts shows REALLY good results, but in most other third-party benchmarks, people realize it's not really SOTA, even bellow Kimi K2.6 and GLM-5/5.1 In my tests too[0], it doesn't reach top 10. One issue, which they also mentioned in their post, is that they can't really serve well the model at the moment, so V4-Pro is heavily rate-limited and gives a lot of timeout errors…

> V4-Pro is heavily rate-limited and gives a lot of timeout errors when I try to test it. This shouldn't be an issue though, considering the model is open-source

Why does it matter if the model/architecture/weights are open source or not, given it's their proprietary inference hardware they're currently having issues with? Proprietary or not, the same issue would still be there on their platform.

Re: DeepSeek v4

#725

Post by armanj »

I have a few lightweight apps using deepseek api, and funny how the initial credit I topped up for using r1 is still left. Nothing makes the user happier than getting more for less. cc: anthropics with its fancy token-wasting claude code "features"

Re: DeepSeek v4

#726

Post by scyclow »

Ladioss wrote: post #376
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…

I always find it an illuminating experience about the power of mass propaganda every time I see an American believe they somewhat have the moral high ground over China, despite starting a new war somewhere around the globe either for petrol or on behalf of Israel every six months.

As an American, I can conclusively say that we absolutely have no moral high ground whatsoever. But bringing the topic back to LLMs, I don't feel great about using an LLM that has a panic attack any time I ask about Tiananmen Square or Taiwanese sovereignty.

Re: DeepSeek v4

#727

Post by ksymph »

carrja99 wrote: post #707

Heh, my eighty year old neighbor uses DeepSeek. Everytime we catch up she tells me about all the new uses she has for it.

Same with my parents! It's the only one they use. I think the simple and stable web interface goes a long way; the ChatGPT site (for example) bombards you with popups, new buttons, and opaque daily limits, while DeepSeek's is pretty consistent and straightforward.

DeepSeek also tends to follow prompts more closely IME, plus the thinking is shown, so I think it's able to register as a 'tool' more easily for the non-tech-inclined for whom that appeals.

Re: DeepSeek v4

#729

Post by LZ_Khan »

It's easy to praise Deepseek for its results and generosity -- how they can keep up with frontier labs on Huawei chips for a fraction of the cost! -- but let's not forget a big part of their toolkit is heavy distillation of SoTA.

Re: DeepSeek v4

#730

Post by vslira »

koe123 wrote: post #355
jurgenburgen wrote: post #330

Earlier quoted context omitted.

I don’t know if we’re ahead of the curve but that tired feeling has started turning into hate here in the EU. I guess being threatened with invasion does that to you. The next decade is going to look very different with America Alone.

I grew up in the states when I was younger, always feeling some closeness to Americans even after I moved back to Europe. With all that goes on it has changed. Recently I sat on a plane near some Americans discussing their holidays here, and I noticed I felt contempt. Sitting their with insane privilege as their government torches the world. Individuals remain individuals, and one really ought not to be prejudice. Ho…

> In France cars are torched if the pension age is raised.

Democracy is… an organized group toppling decisions made by popularly elected representatives within the confines of the law?

Post reply on HN