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

161–170 of 362 posts

Re: DeepSeek-V4-Flash Update

#161

Post by ilaksh »

sparse-Matrix wrote: post #140
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've been having better-than-most performance using qwen3.6 to write python/flask. I tried using it to generate some rust code yesterday, and it generated much code but only ever came within 1 error of a testable build. The 4th or 5th full rewrite is sitting in the buffer right now. I'm currently looking to up my game with Bottlecap AI's return of qwen3.6, 'thinking cap'. Alleged to be twice as fast and superior at c…

You should specify which model size and quant because there are many of both.

Re: DeepSeek-V4-Flash Update

#162

Post by ilaksh »

baalimago wrote: post #31

Very promising. So it will both keep the speed and reduced price, yet exceed performance of the quite sufficient deepseek-v4-pro? Should be extending the lead in intelligence/cost index, as deepseek-v4-flash already were the most price efficient model, which now becomes even better. Although, in the deepseek APIs, the cost is leaking all information about codebases to China.

Supposedly better than GLM 5.2 according to at least one benchmark.

Re: DeepSeek-V4-Flash Update

#165

Post by flexagoon »

ngl999 wrote: post #101
flexagoon wrote: post #85

Earlier quoted context omitted.

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

Probably not real 5.6 Sol

How so? The code and reasoning patterns certainly match, so does the intelligence level. I probably wouldn't know if they're secretly serving Luna instead of Sol, but it's definitely an OpenAI model.

Re: DeepSeek-V4-Flash Update

#166

Post by k__ »

throwa356262 wrote: post #127
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…

What harness are you using to achieve that level of token caching?

I'm using pi and my caching is ~99%.

Re: DeepSeek-V4-Flash Update

#167

Post by ilaksh »

I wonder when the antirez/ds4 group will have an update to their high accuracy 2 bit quant.

Although it's funny that I am thinking about that at all because I have a 2060 :P . My local inference is playing with Gemma 4 E2B and MiniCPM 5 1B.

Re: DeepSeek-V4-Flash Update

#168

Post by _superposition_ »

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…

Among countless other experienced engineers... The cognitive dissonance here is frightening.

Re: DeepSeek-V4-Flash Update

#169

Post by lionkor »

a20eac1d wrote: post #147
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…

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/0a8b080fe45306213efddf3ebb75...

- references/review-workflow.md: https://gist.github.com/lionkor/d2d374b133ceb7e3660bd530ee72...

- references/section-rules.md: https://gist.github.com/lionkor/8a9e503adc7fd3697410cf021f27...

I'm aware that almost all of this is prompt voodoo, and there's no guarantee for the review to find anything or everything, but making it a dedicated skill and thoroughly observing the output thinking, tool calls, and result, lets me adjust these over time and fill the weak spots with even more prompting.

I use this skill by simply telling the agent something like "Review the changes on the current branch against origin/main, take special care with backwards-incompatible changes to the public API" or something like that.

I use `pi` (pi.dev) with a subagents extension, so that I can ask the agent to invoke a subagent to do the review, on work that the agent did.

For models, I use the highest possible reasoning on whatever model I feel like makes sense, usually this is GPT-5.5 or deepseek flash/pro, depending on the confidentiality of the codebase, on the highest reasoning always (for reviews).

I've also had success with a review checklist, though it doesn't produce an easy to parse (for humans) output: https://gist.github.com/lionkor/054ac2cf241e0765eee2383f0dba...

This is why my review skill mandates a very strict output contract. I need the output to be very easy to parse, and the output contract I've specified there does that.

In general I let author and review SKILL.md and similar large prompts, usually with a ruleset like this, which is a 1600 line research artifact from a long GPT 5.5 "Pro" research session on prompt engineering: https://gist.github.com/lionkor/71498794d0a7d72173fc58766f25...

Does the review catch all issues? Not at all. Does it catch, usually more than one, important issue, across large changesets? Absolutely, and that's the point! :)

Feel free to ask me any questions, I'm also happy to share more about my setup via email or add you or anyone else to my private repos with more of these.

Re: DeepSeek-V4-Flash Update

#170

Post by lionkor »

throwa356262 wrote: post #127
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…

What harness are you using to achieve that level of token caching?

I use pi, and, like the sibling comment, the caching ratio is fantastic. I work on C#, Rust, C, C++, shell scripting, and other areas.
Post reply on HN