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

91–100 of 362 posts

Re: DeepSeek-V4-Flash Update

#92

Post by dannyw »

dnhkng wrote: post #11
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…

Totally! This with DwarfStar delivers usable local AI (I hope!)

Usable local AI has been here for a while, esp on say a 5090.

You can’t treat Qwen3.6 like its fable, but if you prompt precisely and specifically it’s a great executor.

I actually found it refreshing to use more of my brain for once, and actually have to think deeper about what I’m trying to do, and how to build it.

Re: DeepSeek-V4-Flash Update

#94

Post by innis226 »

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…

But doesn't it hallucinate a lot? Does that affect your workflow?

Re: DeepSeek-V4-Flash Update

#95

Post by dakolli »

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…

[flagged]

Re: DeepSeek-V4-Flash Update

#96

Post by yuzuquat »

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…

reminds me back in the day when we used to do version control with google drive. you generally don't need to do this anymore i don't think. it should be fairly trivial to open the codex cli in the project directory, ask it to do some analysis and planning -> save to md. then opencode with deepseek to read that md and start implementing. consider that some cross-model subagent workflows already exist: i use claude/fable to plan and there are openai plugins to directly spin up codex subagents. this latter approach gives claude/fable more directly control to babysit the codex agents whereas the former is more of a clearcut handoff

Re: DeepSeek-V4-Flash Update

#97

Post by ncphillips »

dakolli wrote: post #95
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…

[flagged]

For doing what?

Re: DeepSeek-V4-Flash Update

#98

Post by cbg0 »

wkcheng wrote: post #26

If the benchmarks are real and reflect actual use, then this is an insane model. This 300B model outperforms the previous DS4 Pro preview model (1.8T params), and it looks like it outperforms GPT 5.6 Luna too. And it's still cheaper than Luna, even with the price decrease. Crazy.

On DeepSWE Deepseek is 54.4% and Luna is 67%

Re: DeepSeek-V4-Flash Update

#99

Post by cthulberg »

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?

https://github.com/obra/superpowers

I use Opus/Sol with for /brainstorming, deepseek (on Pi) for /subagent-driven-development

I love it, the docs are easily editable and when I'm ready Deepseek is faster/cheaper then everything on my coding plans.

Re: DeepSeek-V4-Flash Update

#100

Post by kzrdude »

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 notice any improvements with this update?
Post reply on HN