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

81–90 of 362 posts

Re: DeepSeek-V4-Flash Update

#81

Post by embedding-shape »

markasoftware wrote: post #77
embedding-shape wrote: post #56

Earlier quoted context omitted.

> Also, it will never complain about security guards, I've been using it to reverse engineer binaries. Maybe I'm using too weak language in my prompts, but none of the OpenAI models I've used via codex has refused to reverse engineer binaries, is it supposed to? I'm sitting right now reverse-engineering a 3rd party firmware together with Codex and haven't hit a single guardrail. Meanwhile, I see people complaining ab…

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

Oh yeah, back in the GPT3.5 days I think, that's probably it. Thanks for sharing your hunch :)

Re: DeepSeek-V4-Flash Update

#84

Post by mordae »

I was just using it when it landed. It started reasoning more extensively from nowhere and precision went up a lot. It also changed its prose style for the better. Looking forward to weights.

Re: DeepSeek-V4-Flash Update

#85

Post by flexagoon »

markasoftware wrote: post #77
embedding-shape wrote: post #56

Earlier quoted context omitted.

> Also, it will never complain about security guards, I've been using it to reverse engineer binaries. Maybe I'm using too weak language in my prompts, but none of the OpenAI models I've used via codex has refused to reverse engineer binaries, is it supposed to? I'm sitting right now reverse-engineering a 3rd party firmware together with Codex and haven't hit a single guardrail. Meanwhile, I see people complaining ab…

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

Re: DeepSeek-V4-Flash Update

#88

Post by rdsubhas »

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…

How can one set topp and temperature in pi?

Re: DeepSeek-V4-Flash Update

#89

Post by petu »

ra wrote: post #49

What's the best way to run this on a 64GB M2 Pro?

Weights are yet to be released (maybe in 24H, Deepseek has track record of releasing same day).

https://github.com/antirez/ds4 is often mentioned for DS4F on Mac, but 64GB is likely not enough to achieve reasonable speeds (official weights should be ~160GB).

Re: DeepSeek-V4-Flash Update

#90

Post by embedding-shape »

rdsubhas wrote: post #88
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…

How can one set topp and temperature in pi?

You build it as an extension or create your own fork/copy of pi and add it. This basically goes for most things in pi, except the most basic stuff. It's basically meant for people who think "I'll just add that myself" rather than expecting it to be there out of the box or finding other's solution to it, for better or worse.
Post reply on HN