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

141–150 of 214 posts

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

#141

Post by kamranjon »

packetlost wrote: post #112
gcanyon wrote: post #108

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. Just the risk of such a thing means regression testing every time you update the model, and you want to be able to run that testing on your schedu…

> 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.

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

#142

Post by cyanydeez »

jmathai wrote: post #139
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…

LLMs add enough nondeterminism to a workflow. Swapping them without the user knowing adds substantially more.

relying on cloud models for anything that gives you ROI is tying a loose noose.

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

#143

Post by jmathai »

cyanydeez wrote: post #142
jmathai wrote: post #139

Earlier quoted context omitted.

LLMs add enough nondeterminism to a workflow. Swapping them without the user knowing adds substantially more.

relying on cloud models for anything that gives you ROI is tying a loose noose.

This is true :P.

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

#144

Post by mmastrac »

I've been trying out the 4.1 flash preview for some bulk tasks: it did a pretty good job refactoring a bunch of .metal kernels to .cu. It needed less steering than Opus on refactoring, IMO, and writes better comments. It failed to port a root exploit from modern Android to an older Pixel 3, but I suspect part of that might have been harness configuration (it asked me to give it a longer timeout for tasks at some point, but I didn't have a chance to finish that).

I was getting something like 300-400 tok/s which was just insanity. It was running so much faster than the toolcalls themselves. Honestly, even if it's not quite as strong in reasoning, it just throws so much so fast that it can do a lot more than you might expect.

I'd say it was comparable with GLM5.3 Flash.

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

#145

Post by alightsoul »

dude250711 wrote: post #59
swiftcoder wrote: post #4

If they can keep up this cadence of Flash leap-frogging the previous Pro, we're in for a good time

Anthropic/OpenAI might step up their anti-distillation defences though.

Anti distillation is just American nationalistic marketing, the amount of data they have "distilled" makes no difference. Deepseek "distilled" like 10000 messages? That's clearly not enough. You gain a lot more doing RL in house.

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

#147

Post by ycui7 »

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…

llm is not a deterministic program. the same model won't even return deterministic answer. what's the point keep the model freezed?

if you want deterministic returns, you should set the temperature to 0 to get the best possibility of deterministic.

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

#148

Post by g023 »

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…

its probably more expensive to run, and I'm thinking 4.1 flash is a smaller more efficient model. You can always host your own. This is what they need to do to stay competitive.

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

#149

Post by bicx »

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 wonder if this is a sign of things to come for dirt-cheap model hosting: no servers running old versions, only new versions. Just to keep costs down.

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

#150

Post by nolok »

tomrod wrote: post #105
nolok wrote: post #103

Earlier quoted context omitted.

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.

Nope, strong disagree. The model is one small part of the process harness; behaviors are usually routable with expected propensities. Unexpected model changes avoiding change management messes with monitoring and observability thresholds. Stochastic controls are a real thing when you have your distributions defined; your workflows on a new model will throw that expected prior out the window.

I think it depends on the workload, which put you in the right (in some case, it's dangerous to do that), but for me even for very clean always correct path I always assume a model can, at time, have a vector brain fart (because it keeps happening).

Also in principle it's similar to Anthropic downgrading.

Personally I use the basis that if I don't self host (I include remote host, but that I pay per hosting nor per model or api), it can change behavior without me asking. But they shouldn't, but it doesn't matter that's what they do.

Post reply on HN