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

DeepSeek launching v4.1 flash cheaper and more capable than v4 pro

news.ycombinator.com

Post reply on HN
Print view View original

181–190 of 222 posts

Re: DeepSeek launching v4.1 flash cheaper and more capable than v4 pro

#181

Post by efficax »

darkoob12 wrote: post #23
EbNar wrote: post #15

Since a few months, I almost exclusively use the Chinese "flash" models for my needs. They are a joy and they cost pennies per answer. Great job.

My mental bias always kept me away from Chinese models. Because i know that china is a surveillance state and all the things we know about CCP. But after what we learned about OpenAI and how they most likely used user data to basically cheat in an open competition i think it does not matter which AI provider you use all of them will own your data and all of them can spy on you. So I am willing to switch to Chinese mo…

the US is also a surveillance state except about 80% of the surveillance is private companies (that are closely tied to the state)

Re: DeepSeek launching v4.1 flash cheaper and more capable than v4 pro

#182

Post by happycube »

monster_truck wrote: post #176
aftbit wrote: post #67

>In keeping with our commitment to user responsibility, following the official launch of V4.1 Flash and prior to the release of V4.1 Pro, all requests to the Pro model will be routed to V4.1 Flash and billed at Flash's price Please don't do this kind of thing. If a user has validated a workflow on V4 Pro, they might not want to suddenly start testing it in production on V4.1 Flash. Instead, keep V4 Pro around but dep…

I'm not sure that anyone is running production workloads against an API that bills twice as much for a chunk of the day. One of the best things about Deepseek is that you can host it yourself and get a ridiculous multiple of usage for what the same dollar amount would yield from their API

It'd be very expensive to get a setup that can run non-flash well.

If they were still at original price I'd get a couple of DGX Sparks myself to run Flash models at a decent quant/context combo.

Re: DeepSeek launching v4.1 flash cheaper and more capable than v4 pro

#183

Post by HansHamster »

atwrk wrote: post #124
HansHamster wrote: post #36

Earlier quoted context omitted.

I must be doing something wrong. I gave v4 pro a try a couple of days ago, gave it a simple prompt like "clean up functions x and y in file z" and it would always start off promising, just to quickly get sidetracked, start hallucinating problems in the code, and just get stuck for hours until I interrupt it: — hmm — 0x2D696370 — little-endian bytes: 70 63 69 2D = 'p','c','i','-' — hmm — WAIT — WAIT — !!!!! — *WAIT —…

I guess this was a heavily quantized version from openrouter? I've never had that experience in the last months of quite intensive use of the official deepseek api.

No, that was directly from deepseek. And it happened very consistently (3 or 4 times in a row, clean session every time, and across 2 harnesses). Guess I'll give it another try when v4.1 flash is available.

Re: DeepSeek launching v4.1 flash cheaper and more capable than v4 pro

#184

Post by nolok »

switchbak wrote: post #180
nolok wrote: post #152

Earlier quoted context omitted.

Yeah but then it doesn't matter if it's "the model changed to another one" or "the model changed but it's the same name". Point is, you're not hosting it, as far as you know it can change at any moment, build around that idea. Is that great no, is that ideal no, that's why I self host (I include actually renting online the capacity and hosting the model myself on it).

You've added a similar response like 5 times, but I don't see you adding more information. Yes - model hosts can do nasty things to you aside from changing the underlying model. That doesn't mean it's cool to have them change the model automatically. Yes, it would be preferable to have complete control over your model serving, and no - not everyone is in a position to do that themselves.

[dead]

Re: DeepSeek launching v4.1 flash cheaper and more capable than v4 pro

#185

Post by mattmcal »

CharlesW wrote: post #62
mattmcal wrote: post #57

Earlier quoted context omitted.

It's not just web chat, V4 Flash 7/31 suffers from a lot of pathological behavior in coding harnesses as well, e.g. infinite loops, hallucinations, premature termination, and invalid tool calls.

FWIW, I haven’t experienced any of that using V4 Flash via DeepSeek in omp. What’s your coding harness and inference provider?

OpenCode but I variously use DeepSeek API/OpenRouter/Vercel AI gateway. I'm sure it's the combo of model + inference provider that is the issue and not the model alone. DeepSeek API also has far better inference speed and reliability than the cheapest providers. That said I never seem to have these issues when using GLM 5.3 flash served by OpenRouter/Vercel.

Re: DeepSeek launching v4.1 flash cheaper and more capable than v4 pro

#186

Post by tempoponet »

pimeys wrote: post #93
mattmcal wrote: post #57

Earlier quoted context omitted.

It's not just web chat, V4 Flash 7/31 suffers from a lot of pathological behavior in coding harnesses as well, e.g. infinite loops, hallucinations, premature termination, and invalid tool calls.

All of these flash models have this. You have to build your harness so that it deals with it. Infinite loops are solved by having an error message that says what to do differently on failure, invalid tool calls are solved by making the tool schema less strict and detect things in the runtime etc. Hallucinations you can't fix. Gemini is a bit worse there than DeepSeek, but there's not much research on how to fix that.…

Can you share what tools and processes you're using to do this?

I've been using Pi to build custom extensions and wrapping workflows in shell processes to make it more deterministic and enforce certain validations, all guided by Fable. This isn't production work, though, just playing llm factorio at home.

Re: DeepSeek launching v4.1 flash cheaper and more capable than v4 pro

#187

Post by declan_roberts »

What are people using in place of the cowork web/chrome integration? I find that to still be compelling reason to use Claude. Sometimes I have a menial task that involves a lot of web browsing/clicking/searching and it's much easier to let claude using my existing browser/login. I haven't find a replacement for it.

Re: DeepSeek launching v4.1 flash cheaper and more capable than v4 pro

#188

Post by notatoad »

simonw wrote: post #49

> all requests to the Pro model will be routed to V4.1 Flash and billed at Flash's price If I'd carefully tested and optimized prompts against Pro I wouldn't be keen on this particular news. I feel like API model providers should lean towards not swapping out models on their paying customers, no matter how much "better" the new model is meant to be.

Seems to be lots of people in here worried about “if i had”, and nobody who actually has done this.

Anybody actually using deepseek in a production system affected by this want to share their experience?

Re: DeepSeek launching v4.1 flash cheaper and more capable than v4 pro

#189

Post by hyperpape »

nolok wrote: post #165
hyperpape wrote: post #162

Earlier quoted context omitted.

Crossing the street and Russian roulette both have non-deterministic risks of injury. And yet I would be bothered to find out that that on my way to work, I was playing Russian roulette by surprise.

Yes and if you decide to play not using a game rulebook but a website that call it "game A" you can't be shocked if "game A" switched from one to the other, even though the doc said opposite yesterday.

That would absolutely be a dick move on the part of the website and would confuse users.

Also, in this case, the game name is not “Game A” but something like “Deep Seek v4 Pro”, which they have previously chosen to use to describe Deep Seek v4 Pro, not Deep Seek v4.1 Flash.

Re: DeepSeek launching v4.1 flash cheaper and more capable than v4 pro

#190

Post by gpugreg »

dandaka wrote: post #166
badatnames wrote: post #154

Earlier quoted context omitted.

I imagine they're doing this due to capacity issues or somesuch. They can always relaunch Pro later, meanwhile a little ricered benchmaxxing of their existing flash model provides a temporary cover story. They certainly aren't silly enough to think this won't impact existing Pro users

They could raise prices, if capacity is problem

They did, but it was not well-received. Perhaps they want to try something different.
Post reply on HN