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

DeepSeek V4 Pro 0813

openrouter.ai

Post reply on HN
Print view View original

261–270 of 493 posts

Re: DeepSeek V4 Pro 0813

#261

Post by XCSme »

ljlolel wrote: post #250
XCSme wrote: post #187

Again, I will wait until there's a provider that doesn't train on prompts before I will benchmark.

I built TrustedRouter so this can fail closed. min_privacy=zdr rejects the request when the model has no ZDR provider; confidential requires provider-side confidential compute. https://trustedrouter.com/blog/how-confidential-computing-pr...

I don't understand how this works?

Is it another proxy on top? What stops the provider from reading/storing the prompts at the LLM execution level?

Re: DeepSeek V4 Pro 0813

#262

Post by gnunez »

bigmadshoe wrote: post #198
jklmnopqrstuvw wrote: post #65

Tested both DS v4 pro 0813 and Grok 4.6 (all from openrouter) on Codex cli. Worked on a same new feature development on my project. Deepseek 4 pro: Worked for 12m 02s - cost $0.12 - has bug. Grok 4.6: Worked for 3m 18s - cost $ 1.41 - no bug.

Why are people giving these n=1 comparisons like they mean anything? The worst offender is that pelican guy. These are non-deterministic systems and a single trial should not update your priors much at all. Of course it's significant that your response had a bug and took four times longer, but if you're only going to try once, this isn't real science, it's just vibes.

I don’t understand why people are calling these transformers models non-deterministic? Are you referring to the temperature parameter? I haven’t played with transformer internals in a while but my understanding is that if the temperature is fixed at a value where the top logit is always picked, then because they weights are fixed, the exact same input should produce the exact same output. Am I missing something?

Re: DeepSeek V4 Pro 0813

#263

Post by monster_truck »

notatoad wrote: post #151
Eueudhsbsj32 wrote: post #31

Earlier quoted context omitted.

What's the new pricing? The prices on OpenRouter still look the same.

nobody is saying. just "more". but openrouter says they don't expect the price to change other than through the deepseek api, other people hosting the same model will keep charging the same price.

It's just a flat 1.5x during peak hours, they emailed this to everyone 2 months ago.

So still effectively limitless.

Re: DeepSeek V4 Pro 0813

#264

Post by echelon »

Palmik wrote: post #173

Why does this link to OpenRouter, which has no useful information on its own? Linking to the official API or the benchmarks would make more sense: - https://api-docs.deepseek.com/ - https://x.com/ChrisGPT/status/2087572834650407024/photo/1 (officially posted on WeChat, this is just one of many reposts)

Moreover, OpenRouter is NOT Open Source, fair source, source available, etc. It's a proprietary cloud service that got first place in the API aggregation distribution game.

Link to DeepSeek!

Re: DeepSeek V4 Pro 0813

#265

Post by gpm »

gnunez wrote: post #262
bigmadshoe wrote: post #198

Earlier quoted context omitted.

Why are people giving these n=1 comparisons like they mean anything? The worst offender is that pelican guy. These are non-deterministic systems and a single trial should not update your priors much at all. Of course it's significant that your response had a bug and took four times longer, but if you're only going to try once, this isn't real science, it's just vibes.

I don’t understand why people are calling these transformers models non-deterministic? Are you referring to the temperature parameter? I haven’t played with transformer internals in a while but my understanding is that if the temperature is fixed at a value where the top logit is always picked, then because they weights are fixed, the exact same input should produce the exact same output. Am I missing something?

Well, yes and no.

By non-deterministic I think people really mean "chaotic" in the chaos theory sense. Small perturbations in the input lead to wild and unpredictable changes in the output. Even with temperature parameters a fixed PRNG seed could mean an LLM was just chaotic and not technically non-deterministic.

But more literally while LLMs are in theory deterministic (though perhaps not inference providers implementations if there's anything like a race condition affecting how things are rounded when added together) - we use the LLMs in harnesses that aren't. There are very likely races in the terminal outputs, dates both intentionally put in the context and accidentally leaked to the context, things like that.

Re: DeepSeek V4 Pro 0813

#266

Post by stavros »

coredog64 wrote: post #96
alecsm wrote: post #50

I've been using the last Deepseek Flash update for a week and I'm amazed. It was a capable model for easy tasks but now it looks like it can do some heavy development for peanuts. I can't wait to try this new one.

IME I can't trust it to write it's own plans from a spec, but if I give it a detailed execution plan written by Opus, it's fast and cheap (if chatty) in executing it.

This is what I do, and it works fantastically well. Just make sure you have Opus/GPT review after.

Re: DeepSeek V4 Pro 0813

#267

Post by monster_truck »

Have been letting it spin pretty hard (~$12.50 for 2B, 50% cache hits) on my traffic simulator/distributed physics engine all day, it's found some pretty significant gains without introducing any new problems.

I'm happy

Re: DeepSeek V4 Pro 0813

#269

Post by Perenti »

Graphs without labels and/or scales on the axes are useless. I know less after viewing that page than before, but I got to see some pretty lines that I guess must mean something.

Re: DeepSeek V4 Pro 0813

#270

Post by simonw »

Palmik wrote: post #173

Why does this link to OpenRouter, which has no useful information on its own? Linking to the official API or the benchmarks would make more sense: - https://api-docs.deepseek.com/ - https://x.com/ChrisGPT/status/2087572834650407024/photo/1 (officially posted on WeChat, this is just one of many reposts)

DeepSeek really need to provide a PAGE for this model release. There's no blog post, there's not even a tweet. It's very unclear what we can link to!
Post reply on HN