DeepSeek-V4-Flash Update • Hacker News Board

Re: DeepSeek-V4-Flash Update

#271

Post by genxy » Fri, Jul 31, 2026, 5:12 PM UTC

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!)

Parent is referring to https://github.com/antirez/ds4

Re: DeepSeek-V4-Flash Update

#272

Post by genxy » Fri, Jul 31, 2026, 5:13 PM UTC

flexagoon wrote: post #85

markasoftware wrote: post #77

Earlier quoted context omitted.

Have you completed the identity verification? It's much more lenient once you have

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

Because they have gone through identify verification, they are more likely to have done that to increase reputation score.

Re: DeepSeek-V4-Flash Update

#273

Post by genxy » Fri, Jul 31, 2026, 5:17 PM UTC

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..

At least you get based models back at some point. You supply data, they supply compute and open weights.

Re: DeepSeek-V4-Flash Update

#274

Post by u8080 » Fri, Jul 31, 2026, 5:19 PM UTC

dghlsakjg wrote: post #248

u8080 wrote: post #80

Earlier quoted context omitted.

Try to use DS platform directly - cheaper and better than openrouter, no subscription

Openrouter has cheaper inference than deepseek for the prior version of v4 flash, which I suspect will happen within a day or two with this version, and they don’t offer subscriptions. Are you confusing it with opencode?

No, maybe I've checked too much time ago, but direct DS was cheaper for all versions - also I had issues with openrouter providers availability

Re: DeepSeek-V4-Flash Update

#275

Post by sudosysgen » Fri, Jul 31, 2026, 5:26 PM UTC

applicative wrote: post #223

riskd wrote: post #204

Earlier quoted context omitted.

Decades of xenophobic propaganda

No, reading Xi's speech. They aren't going to give their Mythos - presumably a few months away - to the Sinaloa cartel or Uighur hackers or the US military or etc etc

Mythos is Fable without safeguards. Open weight models are already essentially at the Mythos level, and with extra post training a well resourced actor could deploy would almost certainly be significantly better than Mythos at hacking. Whatever their threshold is, it's much higher than that.

Re: DeepSeek-V4-Flash Update

#276

Post by rzerowan » Fri, Jul 31, 2026, 5:27 PM UTC

lionkor wrote: post #169

a20eac1d wrote: post #147

Earlier quoted context omitted.

Can you give more info on how you use/prompt those LLMs for code review and what kind of prompts you use? I've had worse experiences doing it because the quality of answer has been quite bad, and I'm wondering if my methods are the reason.

Yes, gladly! I have not yet open-sourced my skills etc., but I can give some insight and share a couple here. Review is a skill, as in, a SKILL.md with a folder full of references: - SKILL.md: https://gist.github.com/lionkor/161525be858d1d75db4c13c0f093... - references/output-contract.md: https://gist.github.com/lionkor/8c68e33becef7a21f8408c7dc119... - references/review-lenses.md: https://gist.github.com/lionkor/0a8…

Which languages are the reviews most successful on in your work so far? Im assumining js/python , would a similar output be feasible on lower level c++ or C#/Java.

Re: DeepSeek-V4-Flash Update

#277

Post by CamperBob2 » Fri, Jul 31, 2026, 5:32 PM UTC

squidbeak wrote: post #124

dakolli wrote: post #95

Earlier quoted context omitted.

[flagged]

An experienced software engineer (read his profile) praises the value he's found in Deepseek, and gives some real data showing how affordable that value is. Then you, dakolli - out of generosity and minute-to-minute devotion to enlightenment - sacrifice time from your busy day to sit down (though perhaps that's been painful lately?) or stand up with your phone - and offer a profound, deeply thought-out counterpoint i…

Look at his history -- he's just here to shitpost. Flag and move on.

Re: DeepSeek-V4-Flash Update

#278

Post by dotancohen » Fri, Jul 31, 2026, 5:33 PM UTC

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…

  > Whatever capabilities they get, can be used "forever" going forward.

"Forever" gets the scare quotes because it is implied only up until the Butlerian Jihad?

Re: DeepSeek-V4-Flash Update

#279

Post by bel8 » Fri, Jul 31, 2026, 5:34 PM UTC

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.

flash for code:

c#, TypeScript, PHP, SQL, CSS, HTML.

also features, tests, fixes, refactoring and planning.

it's super fast, smart and dirt cheap.

Re: DeepSeek-V4-Flash Update

#280

Post by sdesol » Fri, Jul 31, 2026, 5:41 PM UTC

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?

This is self promotional but I am working on making pi extremely enterprise ready with:

https://github.com/gitsense/pi-brains/tree/staging

The README is being worked on but the three videos should give you a good sense of what it can do. Pi is also what makes what I will demo in

https://github.com/gitsense/chat/tree/update-readme

possible. Since Pi exposes so much, it is very easy to build advanced tooling around it to help easily grok hundreds of tool calls to help you understand what they agent knows and what it has tried.