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

111–120 of 1001 posts

Re: DeepSeek v4

#111

Post by fastball »

whateveracct wrote: post #104
simonw wrote: post #63

I like the pelican I got out of deepseek-v4-flash more than the one I got from deepseek-v4-pro. https://simonwillison.net/2026/Apr/24/deepseek-v4/ Both generated using OpenRouter. For comparison, here's what I got from DeepSeek 3.2 back in December: https://simonwillison.net/2025/Dec/1/deepseek-v32/ And DeepSeek 3.1 in August: https://simonwillison.net/2025/Aug/22/deepseek-31/ And DeepSeek v3-0324 in March last year:…

[flagged]

It's just Simon Willison (the person you are replying to) who always makes a pelican, as his personal flippant benchmark. It's not that deep.

Re: DeepSeek v4

#112

Post by post-it »

whateveracct wrote: post #104
simonw wrote: post #63

I like the pelican I got out of deepseek-v4-flash more than the one I got from deepseek-v4-pro. https://simonwillison.net/2026/Apr/24/deepseek-v4/ Both generated using OpenRouter. For comparison, here's what I got from DeepSeek 3.2 back in December: https://simonwillison.net/2025/Dec/1/deepseek-v32/ And DeepSeek 3.1 in August: https://simonwillison.net/2025/Aug/22/deepseek-31/ And DeepSeek v3-0324 in March last year:…

[flagged]

Why is it so wrong?

Re: DeepSeek v4

#113

Post by dewey »

whateveracct wrote: post #104
simonw wrote: post #63

I like the pelican I got out of deepseek-v4-flash more than the one I got from deepseek-v4-pro. https://simonwillison.net/2026/Apr/24/deepseek-v4/ Both generated using OpenRouter. For comparison, here's what I got from DeepSeek 3.2 back in December: https://simonwillison.net/2025/Dec/1/deepseek-v32/ And DeepSeek 3.1 in August: https://simonwillison.net/2025/Aug/22/deepseek-31/ And DeepSeek v3-0324 in March last year:…

[flagged]

No benchmark will be perfect, especially if it's public but it's a fun experiment to visually see how these models get better and better.

Re: DeepSeek v4

#114

Post by CJefferson »

p1esk wrote: post #33
greenknight wrote: post #24

Earlier quoted context omitted.

The thing is, it doesnt need to beat 4.7. it just needs to do somewhat well against it. This is free... as in you can download it, run it on your systems and finetune it to be the way you want it to be.

Do you think a lot of people have “systems” to run a 1.6T model?

To me, the important thing isn't that I can run it, it's that I can pay someone else to run it. I'm finding Opus 4.7 seems to be weirdly broken compared to 4.6, it just doesn't understand my code, breaks it whenever I ask it to do anything.

Now, at the moment, i can still use 4.6 but eventually Anthropic are going to remove it, and when it's gone it will be gone forever. I'm planning on trying Deepseek v4, because even if it's not quite as good, I know that it will be available forever, I'll always be able to find someone to run it.

Re: DeepSeek v4

#116

Post by post-it »

0xbadcafebee wrote: post #70
nthypes wrote: post #5

https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main... Model was released and it's amazing. Frontier level (better than Opus 4.6) at a fraction of the cost.

I don't think we need to compare models to Opus anymore. Opus users don't care about other models, as they're convinced Opus will be better forever. And non-Opus users don't want the expense, lock-in or limits. As a non-Opus user, I'll continue to use the cheapest fastest models that get my job done, which (for me anyway) is still MiniMax M2.5. I occasionally try a newer, more expensive model, and I get the same resu…

What do you run these on? I've gotten comfortable with Claude but if folks are getting Opus performance for cheaper I'll switch.

Re: DeepSeek v4

#117

Post by alecco »

I_am_tiberius wrote: post #69
sidcool wrote: post #45

Truly open source coming from China. This is heartwarming. I know if the potential ulterior motives.

Open weight!

Please don't slander the most open AI company in the world. Even more open than some non-profit labs from universities. DeepSeek is famous for publishing everything. They might take a bit to publish source code but it's almost always there. And their papers are extremely pro-social to help the broader open AI community. This is why they struggle getting funded because investors hate openness. And in China they struggle against the political and hiring power of the big tech companies.

Just this week they published a serious foundational library for LLMs https://github.com/deepseek-ai/TileKernels

Others worth mentioning:

https://github.com/deepseek-ai/DeepGEMM a competitive foundational library

https://github.com/deepseek-ai/Engram

https://github.com/deepseek-ai/DeepSeek-V3

https://github.com/deepseek-ai/DeepSeek-R1

https://github.com/deepseek-ai/DeepSeek-OCR-2

They have 33 repos and counting: https://github.com/orgs/deepseek-ai/repositories?type=all

And DeepSeek often has very cool new approaches to AI copied by the rest. Many others copied their tech. And some of those have 10x or 100x the GPU training budget and that's their moat to stay competitive.

The models from Chinese Big Tech and some of the small ones are open weights only. (and allegedly benchmaxxed) (see https://xcancel.com/N8Programs/status/2044408755790508113). Not the same.

Re: DeepSeek v4

#118

Post by CJefferson »

What's the current best framework to have a 'claude code' like experience with Deepseek (or in general, an open-source model), if I wanted to play?

Re: DeepSeek v4

#119

Post by revolvingthrow »

aliljet wrote: post #61

How can you reasonably try to get near frontier (even at all tps) on hardware you own? Maybe under 5k in cost?

For flash? 4 bit quant, 2x 96GB gpu (fast and expensive) or 1x 96GB gpu + 128GB ram (still expensive but probably usable, if you’re patient).

A mac with 256 GB memory would run it but be very slow, and so would be a 256GB ram + cheapo GPU desktop, unless you leave it running overnight.

The big model? Forget it, not this decade. You can theoretically load from SSD but waiting for the reply will be a religious experience.

Realistically the biggest models you can run on local-as-in-worth-buying-as-a-person hardware are between 120B and 200B, depending on how far you’re willing to go on quantization. Even this is fairly expensive, and that’s before RAM went to the moon.

Re: DeepSeek v4

#120

Post by ind-igo »

0xbadcafebee wrote: post #70
nthypes wrote: post #5

https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main... Model was released and it's amazing. Frontier level (better than Opus 4.6) at a fraction of the cost.

I don't think we need to compare models to Opus anymore. Opus users don't care about other models, as they're convinced Opus will be better forever. And non-Opus users don't want the expense, lock-in or limits. As a non-Opus user, I'll continue to use the cheapest fastest models that get my job done, which (for me anyway) is still MiniMax M2.5. I occasionally try a newer, more expensive model, and I get the same resu…

Agree with your assessment, I think after models reached around Opus 4.5 level, its been almost indistinguishable for most tasks. Intelligence has been commoditized, what's important now is the workflows, prompting, and context management. And that is unique to each model.
Post reply on HN