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

251–260 of 362 posts

Re: DeepSeek-V4-Flash Update

#251

Post by chorizo »

NitpickLawyer wrote: post #3

This is more exciting than k3, IMO. Dsv4 models are extremely cheap to serve. Improving their capabilities has lots of downstream effects, as it becomes "good enough" for more and more tasks. DS was serving the pro version at extremely low prices for a long time, and they've had integrations with opencode & other providers, so they likely gathered a lot of data from real developers doing real tasks (on openrouter the…

Starting to wonder if the free big pickle model on opencode has been DSV4F0731 for the past few months. It’s been incredibly fast and good.

Re: DeepSeek-V4-Flash Update

#252

Post by chorizo »

siva7 wrote: post #232
dannyw wrote: post #91

Deepseek and moonshot are the only two providers I consent to training for.

CCP will be happy! Go on and share all your data with them..

I’m developing open source tools, so happy to have all my context traces be public if it helps improve future models.

Re: DeepSeek-V4-Flash Update

#253

Post by villish »

benjiro29 wrote: post #160
villish wrote: post #20

Earlier quoted context omitted.

> Terminal Bench: Flash 82.7 vs Terra 78.4 Terra 87.4 https://openai.com/index/gpt-5-6/

https://www.tbench.ai/leaderboard/terminal-bench/2.1 > 78.4 The real score is always the official benchmark. We need to see later if DS4 flash 0731 is going to maintain the score but we need to look at the official benchmarks. Already seen a PR for DeepSWE to update the benchmark with 0731, so we can verify claimed vs official.

The comment I replied to was comparing numbers released by each lab, and they made a typo with that specific benchmark.

Re: DeepSeek-V4-Flash Update

#254

Post by davidjade »

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?

I stumbled into this same workflow idea. I hadn't really used anything other that Chat GPT Sol (medium) and when I wanted to start using code agents, I just asked GPT how to start. This evolved into having GPT do the brainstorming and writing the initial prompt for a project feature/change to hand over to Codex working in Sol light mode. These prompts where often a couple pages long as they had a lot of the architecture details worked out already. Codex would then come up with a plan and I'd take that back to GPT to review. GPT would make some suggestions, which I'd throw back to the agent and off it went.

I got super great results working this way. Maybe there is a better way to integrate the two modes though. But my first real project was end-to-end 100% working correctly from the first run - about 10,000 lines (including tests) of greenfield code. I did have it work in manageable chunks that I could easily review - not one-shotting the whole thing.

Now I'm thinking about plugging Deepseek into Codex to be the coding model and see how it goes.

Re: DeepSeek-V4-Flash Update

#255

Post by bwfan123 »

1234letshaveatw wrote: post #215
applicative wrote: post #184

Earlier quoted context omitted.

Xi going to shut down open-weighting of them in a matter of months. No one seriously doubts this. They will be too powerful and they will be gone.

That isn't the Chinese way. They are much more focused on undermine and extinguish. Just look at the European car industry- on its way to being non-existent after the market was flooded, bye bye manufacturing base. Undercut the US AI providers and wait them out, they will go private after they have a stranglehold

> Undercut the US AI providers and wait them out

You could have said the same of linux - that it extinguished proprietary OSs at least for server usecases.

Re: DeepSeek-V4-Flash Update

#256

Post by fdsjgfklsfd »

siva7 wrote: post #232
dannyw wrote: post #91

Deepseek and moonshot are the only two providers I consent to training for.

CCP will be happy! Go on and share all your data with them..

Yes, they trained on my open source code and Wikipedia edits and Stack Overflow answers that I shared freely, so it's only fair that they release their models as open source and share back to the community that created them. I only allow my training data go to open source models.

Re: DeepSeek-V4-Flash Update

#257

Post by sergiotapia »

peperunas wrote: post #55
kmarc wrote: post #53

Essentially I'm running everything on flash now inside pi. With the correct set of MCP servers, context reducer tooling and skills it can implement any task I throw at it. Some sessions take 30+ turns, but it's fast and cheap; all this in an hour, with ~$0.5 cost. (TBH though, in my multi-subagent workflow I do use other, more expensive models for planning, reviewing, oracle-ing) I haven't used our slow opus subscrip…

Do you have any recommendations of such extensions for pi?

I've had a lot of fun with https://omp.sh/ - consider it like zsh -> ohmyzsh

Lots of sensible defaults and good tweaks/settings you just don't worry about.

Re: DeepSeek-V4-Flash Update

#258

Post by fdsjgfklsfd »

applicative wrote: post #222
1234letshaveatw wrote: post #215

Earlier quoted context omitted.

That isn't the Chinese way. They are much more focused on undermine and extinguish. Just look at the European car industry- on its way to being non-existent after the market was flooded, bye bye manufacturing base. Undercut the US AI providers and wait them out, they will go private after they have a stranglehold

Even Xi's speech was as paranoid as Dario Amodei about the possibility of Chinese AI achieving something at the level of say Mythos. If you seriously believe such a thing will be on Hugging Face I really don't know what to say.

DeepSeek-V4-Flash-0731 scores higher than Fable 5 on Terminal-Bench, and Fable 5 is Mythos, correct?

Re: DeepSeek-V4-Flash Update

#259

Post by fdsjgfklsfd »

amelius wrote: post #134

Note: if you are having success with a model, then please post what you are using it for. Writing HTML/CSS is very different from writing Rust/C++ or doing maths.

I use DeepSeek V4 Flash (before this update) for most things:

- OpenCode for codebase editing: python scientific computing and LLM projects

- Open Interpreter Classic (python version) for Swiss army knife terminal replacement one-off task type stuff.

Re: DeepSeek-V4-Flash Update

#260

Post by gravypod »

applicative wrote: post #228
gravypod wrote: post #188

Earlier quoted context omitted.

What would the benefit of this be? If China stops open weights, US labs still have the intelligence frontier. Maybe once Chinese models have speed, cost, and intelligence beat but right now they don't. Undermining out entire economy by subsidizing the release of DIY versions of our main economic drive sounds like a huge win for China.

> Maybe once Chinese models have speed, cost, and intelligence beat but right now they don't. Yes this is why I referred to 'months' and was downvoted by people who can't distinguish their politics from reality. You are restating exactly the text you are criticizing. This is the nature of mechanical parrotlike repetition of propaganda: a) You can have 'frontier' models with closed weights. Your sentence is basically…

If they did have a super powerful secret AI why would avoid:

1. Selling access to the US? 2. Ship more and better software? 3. Talk about it publicly?

If you had a secret AI better than anything currently available the mere mention of this would crater the US tech investment sentiment.

They could even host these Chinese models through AWS and sell at-cost inference on Bedrock and obliterate the US model companies.

Post reply on HN