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

DeepSeek V4 – almost on the frontier

simonwillison.net

Post reply on HN
Print view View original

61–70 of 420 posts

Re: DeepSeek V4 – almost on the frontier

#61

Post by Reviving1514 »

gmerc wrote: post #44
baldai wrote: post #31

Earlier quoted context omitted.

Only similarity it has to Opus 4.6 is the 4 in the name. I do not understand these dishonest comparisons. OOS models are vool, cheap and promising for a future -- but why are we pretending they are better than they are?

Speak for yourself. I found switching from Opus 4.7 to be completely painless and in fact, due to the reliability of Anthropic’s API, less of a friction despite slower response times. Zero issues on a large mono repro

What provider are you using? I have it a shot through open router and saw some weird half formed words coming through occasionally, would love to switch over and give it a proper go

Re: DeepSeek V4 – almost on the frontier

#62

Post by tomjuggler »

So I'm involved in an open source AI cli coding assistant called Cecli (cecli.dev) which is specifically designed to work well with DeepSeek.

DeepSeek is a great model, and Cecli is all about efficiency. It works great for my purposes - agentic programming on a budget.

Re: DeepSeek V4 – almost on the frontier

#63

Post by zozbot234 »

sylware wrote: post #60

If I want to run 'coding prompts' running the biggest deepseek model on CPU, what is the order of time I will have wait, hours, days?

DeepSeek V4 Pro has about 25GB worth of active parameters, so if you can fit the whole ~870GB weights + cache in RAM your tok/s is bounded above by 25GB divided into your system memory bandwidth in GB/s. If you can't fit your whole model in RAM you'll be bottlenecked to some degree by storage bandwidth which is in the single or low double digits in GB/s.

Mind you, it's an absolutely sensible setup either way if you are just testing a few queries and are willing to run them unattended/overnight. Especially since the KV-cache size is apparently really low (~10GB is said to be typical) so you get a lot of batching potential even in consumer setups, which amortizes the cost of fetching weights.

Re: DeepSeek V4 – almost on the frontier

#65

Post by Oras »

edg5000 wrote: post #56

Has anybody used V4 hard, for the most challenging tasks (agentically, locally)? It's so hard to compare without putting serious time in it. Like spending a year daily with the model.

I tried it for two tasks using Claude Code, on max effort.

1. Web platform, asking it to analyse a feature to create reports, and coming up with better solution and better UX. it did great, I would say on par with Sonnet 4.6 or even opus considering the thinking and explanation

2. Mac app with some basic functionality, it did well from functional perspective but then I used Opus 4.7 to evaluate and suggest improvements, where I noticed it missed many vital points in design system and usability.

I think it’s a leap, I haven’t used a model this capable that is not OpenAI or Anthropic

Re: DeepSeek V4 – almost on the frontier

#67

Post by eckelhesten »

dbeley wrote: post #45
deaux wrote: post #14

I'm surprised that people here don't care at all about these models openly training on your data, especially if you use them straight from the model developer. Whereas things like "GitHub now automatically opts everyone into using their code for model training" get hundreds of justifiably angry comments, I never see this brought up anymore on posts like these talking about using Chinese models through OpenRouter. Thi…

The cool thing about open-weights model is that you are free to use alternative providers that won't phone home to the original model creators. I see 6 alternative providers listed on Openrouter for DeepSeek V4 Pro for example.

At least that’s what they’re telling you. It’s a ”trust me bro” scenario.

I’d rather use the phone home version (deepseeks own endpoint). The benefit is that I’m fairly certain that they actually host the model I’m paying for.

Re: DeepSeek V4 – almost on the frontier

#68

Post by eckelhesten »

deaux wrote: post #14

I'm surprised that people here don't care at all about these models openly training on your data, especially if you use them straight from the model developer. Whereas things like "GitHub now automatically opts everyone into using their code for model training" get hundreds of justifiably angry comments, I never see this brought up anymore on posts like these talking about using Chinese models through OpenRouter. Thi…

As opposed to?

Do you really think OpenAI, Anthropic or any other entity in the same business respects your data?

The Chinese AI companies who release open weights actually deserve whatever input you give them. They are the reason why there is competition and not duopolies in the domain.

Re: DeepSeek V4 – almost on the frontier

#69

Post by cheshire_cat »

While the cost are lower than frontier models there are two factors that make DS4 Pro and K2.6 not as cheap as they might look.

For DS4 Pro there's a discount going on for the official API, which sometimes gets overlooked and mixed up in discussions. Simon uses the full price in the comparison, so that's not an issue here.

The other issue is that DS4 Pro and K2.6 often use way more reasoning tokens than the frontier models. In my testing there are certain pathological cases where a request can cost the same as with a frontier model because they use so much more tokens. To be fair I'm using DS and kimi via 3rd party providers, so they might have issues with their setups.

But if you look at the Artificial Analysis pages of the models you'll see that DSv4 Pro uses 190M tokens and K2.6 170M tokens for their intelligence benchmark, while GPT 5.5 (high) only used 45M.[0][1][2]

I recommend looking at the "Intelligence vs. Cost to Run Artificial Analysis Intelligence Index" ("Intelligence vs Cost" in the UI). The open source models are still cheaper to run, but not by as much as you'd think just looking at the token prices.

[0] https://artificialanalysis.ai/models/deepseek-v4-pro [1] https://artificialanalysis.ai/models/kimi-k2-6 [2] https://artificialanalysis.ai/models/gpt-5-5-high

Re: DeepSeek V4 – almost on the frontier

#70

Post by vagrantJin »

deaux wrote: post #14

I'm surprised that people here don't care at all about these models openly training on your data, especially if you use them straight from the model developer. Whereas things like "GitHub now automatically opts everyone into using their code for model training" get hundreds of justifiably angry comments, I never see this brought up anymore on posts like these talking about using Chinese models through OpenRouter. Thi…

You definitely have a bone to pick. Chinese researchers usually have given the world the most cheap and consistent high quality research around LLMs. They don't pretend, they do the work and release the goodies. Mostly so cheap, every one in the world has a chance to use close to frontier models. Why would you respond with "Anger"?

You let us know what your real complaint is about and let's not feign indignation at open models and research.

Post reply on HN