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

101–110 of 493 posts

Re: DeepSeek V4 Pro 0813

#101

Post by logicchains »

bikemike026 wrote: post #89
okamiueru wrote: post #38

Earlier quoted context omitted.

How do you define intelligence? I encounter that kind of sentiment all too often, and I have to assume we go by wildly different understanding of what that might entail.

If you read Opus 5's output, it is beyond the comprehension of virtually all engineers and developers. That is what I mean by intelligence. Math, science, and engineering are all contained in one model. We may be experts in one field. The model is an expert in everything that humans know.

You mean Fable 5 right? Opus 5 makes lots of stupid mistakes about anything that requires any domain knowledge.

Re: DeepSeek V4 Pro 0813

#102

Post by cortesoft »

LeonKnst wrote: post #6

I find it interesting how much adoption seems to be influenced by momentum. Some of these Chinese models are surprisingly capable, but developers often default to the models that are already established as the “industry standard

I keep using Claude and Codex simply because the subscription rates are SO MUCH cheaper than per-token rates, even with the cheaper models

Re: DeepSeek V4 Pro 0813

#103

Post by trollbridge »

networked wrote: post #78
trollbridge wrote: post #54

Earlier quoted context omitted.

Interesting - I've been dropping into MiMo-V2.5-Pro-UltraSpeed whenever Flash seems to be "stuck" and it usually figures it out. I use UltraSpeed just because I'm so frustrated by then that I'm impatient. I still find 5.6-Sol can solve some things neither of those can, but it's so slow (and it's so hard to trace / debug the reasoning) that I just let it run overnight.

What about 5.6 Terra and especially Luna? Luna scores pretty high on benchmarks and seems to have different habits (like a denser pattern of tool use) and blind spots. I'm trying out a development workflow where I generate mundane code with MiMo and Luna (and soon V4 Pro 0813?) and have Opus 5, which is running on only a Pro subscription, review and refactor it. I'm not sure it will justify the context switching, but…

Terra and Luna are fine, but they’re quite slow (OAI seems to be really slow lately) and don’t have the reasoning traces. My workflow really depends on them or I can’t switch models effectively.

Re: DeepSeek V4 Pro 0813

#104

Post by trollbridge »

eli wrote: post #63
Gecko4072 wrote: post #10

Currently burning money quickly on official deepseek api. They are also increasing pricing starting today. V4 Flash 0731 still feels like the most outstanding model of the past few months and probably to come.

The Deepseek official API is good with excellent caching. But their privacy policy is unusually bad - they can train off your prompts and completions.

Use another provider from OpenRouter.

I really don’t care if they train off my prompts.

Re: DeepSeek V4 Pro 0813

#105

Post by hgoel »

bikemike026 wrote: post #89
okamiueru wrote: post #38

Earlier quoted context omitted.

How do you define intelligence? I encounter that kind of sentiment all too often, and I have to assume we go by wildly different understanding of what that might entail.

If you read Opus 5's output, it is beyond the comprehension of virtually all engineers and developers. That is what I mean by intelligence. Math, science, and engineering are all contained in one model. We may be experts in one field. The model is an expert in everything that humans know.

I don't think that's because of its "intelligence". It speaks obtuse techbro-ese: stringing together words that sound smart to obscure the simplicity of the thing it's describing. In many ways it's the opposite of intelligence.

Opus 5 and Fable 5 in particular suffer from this issue at worse level than most models in the same class.

Re: DeepSeek V4 Pro 0813

#106

Post by okamiueru »

bikemike026 wrote: post #89
okamiueru wrote: post #38

Earlier quoted context omitted.

How do you define intelligence? I encounter that kind of sentiment all too often, and I have to assume we go by wildly different understanding of what that might entail.

If you read Opus 5's output, it is beyond the comprehension of virtually all engineers and developers. That is what I mean by intelligence. Math, science, and engineering are all contained in one model. We may be experts in one field. The model is an expert in everything that humans know.

I'd have to ask for you to be more specific, otherwise, to take your answer at face value, it comes across as a contradiction.

> [Opus 5's output] is beyond the comprehension of virtually all engineers and developers

That would make it pretty bad? The key defining quality of good software, is clarity, and the ability to simplify a complex problem to the point of it seeming trivial.

> Math, science, and engineering are all contained in one model. We may be experts in one field. The model is an expert in everything that humans know.

The bar here should absolutely be to judge this against the expert level within each domain. I have time and time come across LLM output being woefully underwhelming in every single request where I am an expert. For all areas that I am not, it sure seems plausible. It is far more likely than not, that it is equally inadequate in the areas I lack the necessary knowledge to tell.

If the AI is being subpar in every field and category compared to an expert in said respective field, then, what a strange gauge of a tool's usefulness. Are we attributing higher value because a single model is "attempting to solve all knowledge and fields at the same time", why is that of any importance, or excuse?

We should not define "intelligence" as how effectively it can convince a non-expert of something being plausible. That sounds like the absolute worst tradeoff. You'd have to waste the experts time in filtering and refuting incorrect postulations that are cheep to generate. The perfect storm for bullshit asymmetry.

Re: DeepSeek V4 Pro 0813

#108

Post by freakynit »

Just tested through openrouter.. gave exactly same task.. the task was to scan existing repo, and generate a single docker-compose file to deploy behind a caddy server, where certain port ranges are already used, the service demands widlcard certificates to be provisioned from outside, and postgre needs to be built-in one...

Tested this model, and gpt-5.6-terra-high.

Results: this one had few issues. terra: none.

These results are consistent with my past observations with the latest flash version as well. What benchmarks say, vs what I've been observing are different.

They are good till the project is simple... not anymore.

Re: DeepSeek V4 Pro 0813

#109

Post by hgoel »

trollbridge wrote: post #71
spacebanana7 wrote: post #26

Earlier quoted context omitted.

In an enterprise setting Chinese models are often discouraged due to political risk. They don't want to need to remove a model that's deeply embedded in their stack. And it's entirely feasible that the US gov bans federal contractors from using them in the next 6 months for example, or that EU AI safety rules effectively ban them too.

Then run the DeepSeek or Qwen model on AWS GovCloud, etc., and you won't have any risk of exposure to "China". I'm not even sure what "EU AI safety rules" are. Can't people in the EU just use whatever they want?

Running on AWS GovCloud isn't necessarily an option, some places prohibit running Chinese origin models even locally.
Post reply on HN