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

DeepSeek-V4-Flash Update

api-docs.deepseek.com

Post reply on HN
Print view View original

341–350 of 362 posts

Re: DeepSeek-V4-Flash Update

#341

Post by apitman »

dotancohen wrote: post #321
idiotsecant wrote: post #310

Earlier quoted context omitted.

I feel like once they make a mega successful movie of a book we can stop doing the secret handshake.

The only movie I've ever enjoyed after reading the book was Jurassic Park. I've never seen the Dune movies or most other book-based movies, but honestly The Martian and Project Hail Mary were tempting. I'll probably surrender to one of those two someday.

I grew up on Dune lore and the first movie is one of my favorites of all time. Highly recommended for any Dune fan. I didn't care for the second one.

Re: DeepSeek-V4-Flash Update

#342

Post by satvikpendem »

applicative wrote: post #297
satvikpendem wrote: post #245

Earlier quoted context omitted.

He explicitly said he wants open weight models at his recent speech at an AI conference in Shanghai: https://news.ycombinator.com/item?id=48970449#48970784

The Chinese equivalent of the expression 'open weights' appears nowhere in this talk. You believed the Western press. Chinese AIs are not typically open. The most important by far is Bytedance.

Openness not open weight. You keep saying this and that was said while not quoting anything, not sure why anyone should take your comments here seriously.

Re: DeepSeek-V4-Flash Update

#343

Post by arjie »

amunozo wrote: post #315
arjie wrote: post #23

Oh my goodness what an update. I need these weights. It's an incredible model for the size. The improved tool calling etc. should be able to make my harness way simpler. This runs at mega-speed on prosumer hardware (2x RTX Pro 6000).

How many tok/s are we talking about?

The old one was 160 tok/s. With DSpark it’s like 250 tok/s or higher. I don’t recall from tbe last time I was looking. You can turn on farther drafting and get more.

Re: DeepSeek-V4-Flash Update

#344

Post by marcus_cemes »

enduser wrote: post #330
marcus_cemes wrote: post #309

Earlier quoted context omitted.

Works out of the box with OpenRouter for most models. Some providers are a bit flaky, but DeekSeek (provider) has been one of the most reliable for me, no problems hitting >99% CH.

The problem is when OpenRouter switches providers..

That's fair, each provider maintains their own cache. OpenRouter does make an effort to keep providers "sticky", but it may hop/stick to another if latency is too high.

If you don't care about latency, you can create a preset with a single provider, then use that as the model key (i.e. `@preset/deekseek-v4-excl`). The only real downside is OpenRouter's service fee. If you don't want the convenience of switching models, or their excellent dashboard, it's definitely better to pay the provider directly.

Re: DeepSeek-V4-Flash Update

#345

Post by erikrothoff »

lionkor wrote: post #50

I use deepseek for a lot of my personal day-to-day agent needs, and I will simply put this here and let this speak for itself, last 30 days: - Cost: $4.55USD - API requests: 3,467 - Tokens: 323,183,886 And as an engineer who leads a small team, I have very high standards for quality, and these carry across to my personal projects where I use deepseek. It has not disappointed at all for coding or review tasks. For eve…

What are the tasks where it falls short?

Re: DeepSeek-V4-Flash Update

#347

Post by flexagoon »

dotancohen wrote: post #282
flexagoon wrote: post #85

Earlier quoted context omitted.

Weird, I'm using 5.6 Sol through Chinese resellers and it reverse engineers stuff just fine

Do you have any suggestions for resellers? My Gmail username is the same as my HN username if you're not comfortable posting that here. Thanks.

I used Byesu and now use a6api. Byesu is a bit more expensive, but a6api is a marketplace so has a higher risk of fake models.

Re: DeepSeek-V4-Flash Update

#348

Post by dannyw »

krapht wrote: post #201
lionkor wrote: post #194

Earlier quoted context omitted.

Sounds like it'll replace v4-flash, v4.1 would be nice to keep both available. On the other hand, it's nice to just get an improvement on anything that asks for "deepseek-v4-flash" without having to change the model string.

I think that's backwards. Anything that changes the performance of a model deserves a minor version bump. A new model has to be qualified before being pushed to production; but we don't get the choice here, just cross your fingers there are no regressions at all on all possible tasks the model might be asked to do.

They dropped the -preview ID.

Re: DeepSeek-V4-Flash Update

#349

Post by dannyw »

embedding-shape wrote: post #67
f6v wrote: post #62

I'm thinking of using ChatGPT for making plans and V4-Flash for execution. Does anyone have good advice on pairing different models?

Pairing non-APIs with APIs tend to be a hassle, and risky, as usually that breaks the ToC. I guess easiest for you to test if it's worth using the OpenAI API, is to manually copy-paste responses between wherever you run V4-Flash and the ChatGPT UI. What I've done in the past is basically .zip up the entire project directory, ignoring files from .gitignore, then asking ChatGPT Pro to inspect that and come up with a pl…

Only for Anthropic. OpenAI officially allows you to use your subscription in non-Codex harnesses / API-like use.

Re: DeepSeek-V4-Flash Update

#350

Post by hgoel »

anigbrowl wrote: post #291
maweaver wrote: post #269

Earlier quoted context omitted.

You are using DeepSeek's services directly? Doesn't that end up sending at least snippets/chunks of code to a server where it is subject to Chinese government data access laws? Even if I was okay with that, my organization would never be. And even if they were, our partners/vendors/customers would not be. I think that's the sticking point for a lot of people.

So go with some other provider who hosts the models like OpenRouter if are worried about this.

Some employers have a policy prohibiting any use of Chinese models, not even allowed to run them locally on air-gapped machines.
Post reply on HN