Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

DeepSeek V4 Flash 0731

arcprize.org

Post reply on HN
Print view View original

301–310 of 477 posts

Re: DeepSeek V4 Flash 0731

#301

Post by mycall »

svachalek wrote: post #204
FernandoTN wrote: post #194

Earlier quoted context omitted.

I think you're overlooking the fact that for long-horizon tasks, even small errors compound over time and can lead to catastrophic outcomes. For simple queries, we have reached the threshold since the beginning of the year, and models are good enough from every provider to make a meaningful difference between one another. (ChatGPT, Claude, Gemini, Grok, MuseSpark, Kimi, DeepSeek, GLM...) The real unlock will be, and…

These are not 24 hours of inference with floating point errors accumulating; largely the system guards against errors compounding. Tool failures, compile failures, test failures, etc, push back against the model taking a wrong turn and force it to correct. Yes it's much easier to have a smarter model that goes straight to the correct answer first, but it may not be necessary or economical. There's a minimum bar for t…

> it's much easier to have a smarter model that goes straight to the correct answer first

That's basically ASI not AGI, if you agree humans are NGI (natural general intelligence) and make mistakes and wrong decisions in solutions all the time. Right steps with some wrong ones is acceptable though for AGI.

Re: DeepSeek V4 Flash 0731

#302

Post by brynnbee »

darkwater wrote: post #166
brynnbee wrote: post #158

Earlier quoted context omitted.

Others have said similar but I disagree, I'm spending $200/m and I can easily burn through my weekly quota with a few overnight goals using 5.6 medium.

And what do you do with all that?

I've reverse engineered multiple classic games and turned them into popular, browser-based MMO-like experiences.

I'm also creating a free platform that replaces extremely out-of-date software, some of it only available with mutli-million dollar contracts, to help medical physics professionals with cutting-edge radiotherapy devices used to treat cancer.

https://brynnbateman.com/ for a list of projects

Re: DeepSeek V4 Flash 0731

#304

Post by apitman »

ignoramous wrote: post #155
NoboruWataya wrote: post #138

My Claude account was banned the other day. The only possible cause I can think of is that I tried to authenticate from the AI assistant in a JetBrains IDE and, not thinking, entered the details for my regular subscription rather than an API account. As soon as it became apparent that I needed an API account rather than a subscription, I just closed out of the tab. Nevertheless, about 20 minutes later I got an email…

> My initial thought was to sign up for ChatGPT, but I had $20 in OpenRouter so I've been trying out DeepSeek V4 Pro with Pi for the last few days and I gotta say, it's good enough for my use case If you prefer subscriptions, OpenCode Go ($10/mo), Cline Pass ($10/mo), Atlas Code ($20/mo), and CommandCode ($1/mo) serve some of the best open weights with generous limits. OpenCode Go currently offers $120 for $10 on Dee…

> OpenCode Go currently offers $120 for $10 on DeepSeek Flash v4

At DeepSeek's absurdly low rates or market rates?

Re: DeepSeek V4 Flash 0731

#305

Post by ccakes »

brynnbee wrote: post #302
darkwater wrote: post #166

Earlier quoted context omitted.

And what do you do with all that?

I've reverse engineered multiple classic games and turned them into popular, browser-based MMO-like experiences. I'm also creating a free platform that replaces extremely out-of-date software, some of it only available with mutli-million dollar contracts, to help medical physics professionals with cutting-edge radiotherapy devices used to treat cancer. https://brynnbateman.com/ for a list of projects

An MMO of Full Throttle would be amazing!

Re: DeepSeek V4 Flash 0731

#306

Post by johnnyApplePRNG »

nylonstrung wrote: post #173

Compared to the last Deepseek V4 Flash version I've had tons of issues with it getting in infinite loops and talking to itself without executing tool calls, wasting tons of tokens This is on Pi agent, nothing fancy at all about my prompts or use case. Anyone else experiencing this? I've also had it randomly go from talking about Rust to talking about the electric chair, controversies about D&D rules (both irrelevant…

What quantization are you using? Which infra provider?

Baseten.co's version got into a loop rather rapidly... I've since added loop detection and adjusted some other settings on the pi coding agent and have yet to notice it again. I also switched to DeepInfra ... who serves an fp4 version admittedly, but I've had no issues with it as of yet and it's the top provider on openrouter.ai volume wise.

Re: DeepSeek V4 Flash 0731

#307

Post by brynnbee »

ccakes wrote: post #305
brynnbee wrote: post #302

Earlier quoted context omitted.

I've reverse engineered multiple classic games and turned them into popular, browser-based MMO-like experiences. I'm also creating a free platform that replaces extremely out-of-date software, some of it only available with mutli-million dollar contracts, to help medical physics professionals with cutting-edge radiotherapy devices used to treat cancer. https://brynnbateman.com/ for a list of projects

An MMO of Full Throttle would be amazing!

It'd be interesting to see what someone could do to turn a 90s era adventure game into an MMO! I never played the game myself but I think basically any game dev project that modernizes stuff is really neat.

Re: DeepSeek V4 Flash 0731

#308

Post by pylotlight »

brynnbee wrote: post #302
darkwater wrote: post #166

Earlier quoted context omitted.

And what do you do with all that?

I've reverse engineered multiple classic games and turned them into popular, browser-based MMO-like experiences. I'm also creating a free platform that replaces extremely out-of-date software, some of it only available with mutli-million dollar contracts, to help medical physics professionals with cutting-edge radiotherapy devices used to treat cancer. https://brynnbateman.com/ for a list of projects

Time to make creative software for linux that can replace adobe for Video/photo editing :P

Re: DeepSeek V4 Flash 0731

#309

Post by natsucks »

namr2000 wrote: post #213
ak_t wrote: post #164

Note this is the 07/31 release of DSv4 flash and not the "preview" that they put out a couple months or so ago. I've been running this model locally for a week, and the preview version before that. This updated one feels like a whole tier up. It's very capable for debugging and analyzing documents/data I upload. The killer feature, IMO, is the speed. On 2x RTX Pro 6000 Blackwell, its ~8k tok/s prefill and ~250 tok/s…

What runtime are you using with the 2x RTX Pro 6000 Blackwell machine? I have the same setup and tried DSv4 Flash on vLLM and ran into a ton of kernel bugs that don't seem to have been fixed yet.

so..you guys have $20k+ rigs?

Re: DeepSeek V4 Flash 0731

#310

Post by jacquesm »

This is the best model to come out since the beginning of open weights models for those working with classified data that you can not use hosted services for. I've been using it pretty much day and night since it landed and I'm nothing short of amazed. You'll need some pretty good hardware to run it though.
Post reply on HN