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

171–180 of 221 posts

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

#171

Post by frde_me »

nolok wrote: post #164
lkois wrote: post #153

Earlier quoted context omitted.

That's a narrow take. Non-deterministic doesn't mean random; workflows can be reasonably validated and consistent to some known degree. I work for an education department that serves a chatbot for students, and model changes go through painstaking content safety reviews. I initially assumed it's just a bunch of bureaucratic paranoia. But every other model upgrade has a measurably different adherence to the existing s…

I work in the same field for one of my company, in europe, and if you're not self hosting sorry but your worries are not something I can accept because models are very much not reliable on that front, let alone when you let the host decide HOW to serve a model (ressources allocated, different version of the same model, etc ...). I'm not being a d**, just saying, the problem you have is something that I have faced EXA…

It's not that you're a d*, it's just that you lack any kind of nuance

There's a whole spectrum between self-hosting open weight models and having a cloud provider swap models from under you

Should you self host a model if want to maximize predictability to the limit? Yes. Does that mean it's wrong for someone hitting a model on API to expect that it won't switch to a completely different model under the hood from one day to another? Probably not.

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

#172

Post by kzrdude »

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 Chinese labs have released interesting papers to accompany their releases too, especially DeepSeek and Kimi. This improves their standing among a few of us, who really like to see and read the papers with details about what they have changed and how their models work.

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

#173

Post by nolok »

frde_me wrote: post #171
nolok wrote: post #164

Earlier quoted context omitted.

I work in the same field for one of my company, in europe, and if you're not self hosting sorry but your worries are not something I can accept because models are very much not reliable on that front, let alone when you let the host decide HOW to serve a model (ressources allocated, different version of the same model, etc ...). I'm not being a d**, just saying, the problem you have is something that I have faced EXA…

It's not that you're a d*, it's just that you lack any kind of nuance There's a whole spectrum between self-hosting open weight models and having a cloud provider swap models from under you Should you self host a model if want to maximize predictability to the limit? Yes. Does that mean it's wrong for someone hitting a model on API to expect that it won't switch to a completely different model under the hood from one…

Sure, but if you're working in a field where that limitation is not "because you like it" but "because you have to" it doesn't matter. If you cannot assume it to be true, then you have to assume it isn't.

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

#174

Post by gpugreg »

nolok wrote: post #103
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…

Usually I would very much agree with you, but those things are not deterministic so if that's an issue for you you're probably not making the right choices.

    > those things are not deterministic
Determinism was an explicit goal of DeepSeek-V4. From their paper: https://arxiv.org/html/2606.19348v1#S3.SS3

    > we implement end-to-end, bitwise batch-invariant, and deterministic kernels with minimal performance overhead
Of course, providers may not implement deterministic inference for various reasons, but it is possible.

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

#175

Post by neodymiumphish »

disiplus wrote: post #160
WhyNotHugo wrote: post #157

Earlier quoted context omitted.

A dice roll is non-deterministic. Replacing a six-sided die for an eight-sided die also keeps rolls non-deterministic. That doesn't mean it's fine to just replace the dice mid-game.

Sure, but they are replacing same generation model to another not just switching opus to gpt.

But it’s more like them swapping Opus 5 for Sonnet 5.5 or something. IMO OP’s right to argue against it.

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

#176

Post by monster_truck »

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

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

#178

Post by kristjansson »

nolok wrote: post #103
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…

Usually I would very much agree with you, but those things are not deterministic so if that's an issue for you you're probably not making the right choices.

The user cares about the distribution of outputs. That distribution is structurally determined by the distribution of inputs (i.e. prompts), the weights of the model, and (these days) the dynamics of the harness guiding successive generations.

The only way to characterize whether a choice is 'right' is to characterize the output distribution (i.e. evals)! Changing the underlying weights necessarily invalidates whatever characterization may have been done. One may assert that one's harness regularizes outputs back toward the desirable distribution, or one may hope the different weights induce a sufficiently similar output distribution.

But no, one should not be completely agnostic to the choice of weights just because there's some nondeterminism.

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

#179

Post by gcanyon »

kamranjon wrote: post #141
packetlost wrote: post #112

Earlier quoted context omitted.

> They’re nondeterministic at a fine level, but can be “deterministic” at a more general level: e.g. you might know that one model will always return properly formatted json when asked. That might not be true of the replacement, even if it is in general “better” and cheaper. This isn't true. Even Sol messes up JSON formatting for me on occasion. Do not delude yourself into thinking these things are reliable. They are…

Is nobody using structured outputs? They use constrained decoding at the generation stage to ensure the probability of tokens that would break the format are set to 0. I kinda figured everyone was doing this at this point.

We use structured output and To my knowledge it has never failed (millions of data points). There seem to be two classes of people: those doing productive work with LLMs, and those who only get replies insulting their mothers…

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

#180

Post by switchbak »

nolok wrote: post #152
idiotsecant wrote: post #110

Earlier quoted context omitted.

Models are not deterministic, but they do have a flavor . When that flavor changes it can change the nature of output in a way that is undesirable. Sort of like shooting a rifle - where the bullets hit is (to some order of magnitude, no philosophizing please) non-deterministic, but different very similar rifles will group differently and need to be appropriately adjusted to hit anything.

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.

Post reply on HN