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

421–430 of 493 posts

Re: DeepSeek V4 Pro 0813

#421

Post by okamiueru »

bikemike026 wrote: post #207
okamiueru wrote: post #106

Earlier quoted context omitted.

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 ar…

I disagree with points 1, 2, and 3. Point 4, AI is better than average, and sometimes it's better than excellent. Point 5 is irrelevant.

That seems awfully self deprecating. Surely, you expect better of yourself in at least some area, than the average competency of humans across all areas?

Re: DeepSeek V4 Pro 0813

#423

Post by KoolKat23 »

thunfischtoast wrote: post #413
Hardd wrote: post #388

Based on my experience so far, compared to previous models, DeepSeek V4 Pro achieves results equal to or even better than before, but at a lower cost.

Sounds like something a DeepSeek V4 Pro bot would say

Passed your personal turing test.

Re: DeepSeek V4 Pro 0813

#424

Post by ricardobeat »

jatora wrote: post #327
polski-g wrote: post #271

Earlier quoted context omitted.

Interesting. I use Flash for making the plans and GPT for execution.

flash for plans?! i don't understand why you wouldnt use something far stronger for the most load bearing point of the project

There aren’t many “far stronger” models than Flash 0731 now, it’s only beaten by Claude and OpenAI models at high/max effort, and everything that matches it costs 5x-10x more.

Re: DeepSeek V4 Pro 0813

#425

Post by okamiueru »

nwienert wrote: post #299
bikemike026 wrote: post #89

Earlier quoted context omitted.

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.

Careful, you may have a bit of psychosis. They are very, very far from incomprehensible, and also very far from the top at least of my field. The best in my field are produce far higher quality results, and I think that's true for all fields. It's just an incredibly good 85% quality machine that experts all use because they can guide it to be up to their quality faster than doing it themselves.

You could take that even further, to the actual danger of reliance of these tools when you lack the expert knowledge. That is, when you assume it took you 100%, but missed the 15% it got very wrong, or perhaps even worse: subtly wrong. This compounds with the next similar task, and either you've made the actual experts quit their job as it has become to babysit LLM output, or you end up with an unusable mess, deleted production databases, etc.

Re: DeepSeek V4 Pro 0813

#426

Post by mlrtime »

miohtama wrote: post #224
Foobar8568 wrote: post #147

Earlier quoted context omitted.

Right now, sol-xhigh is my favorite model. I feel that Opus 5 is dumber than 4.8. Fable is too expensive to do anything (limit of $50, started a prompt at $25, ended up at $75, is bullshit, but at least it's "free credits"). DeepSeek is okay for random API-based stuff, as it's cheap. Local open models running on a 5090 are hit or miss. I feel that most GGUFs/quants are awful...

Opus 5 degrades to word salad. I wonder if it is because of watermarking.

Agreed, I'll get a terminal full of text and I just reply "I don't understand this"

And it retypes it for a human, I'm doing this more and more lately.

Re: DeepSeek V4 Pro 0813

#428

Post by twelvechairs »

thunfischtoast wrote: post #413
Hardd wrote: post #388

Based on my experience so far, compared to previous models, DeepSeek V4 Pro achieves results equal to or even better than before, but at a lower cost.

Sounds like something a DeepSeek V4 Pro bot would say

You are absolutely right!

Would you like me to respond in a more naturalistic way for hackernews denizens?

Re: DeepSeek V4 Pro 0813

#429

Post by agrippanux »

MuteXR wrote: post #405
Art9681 wrote: post #227

Earlier quoted context omitted.

Terra is great. It's wild how different our experiences are. Install the Superpowers plugin. Behold.

In my experience, Superpowers has begun to massively slow down the capable models at this point. The skills they add are incredibly bloated and just get you worse results nowadays, tbh.

I loved Superpowers and evangelized it heavily.

This week I removed it because it now gets in the way of the frontier models.

Re: DeepSeek V4 Pro 0813

#430

Post by Lalabadie »

wut42 wrote: post #329
Lalabadie wrote: post #290

Earlier quoted context omitted.

In my experience, that's the OpenRouter tax. Even a session that does everything right to remain sticky ends up getting moved between providers on a few requests, which bills you the full context as input every time the switch happens. I assume it's done as load balancing/latency mitigation, but it's put me off of OpenRouter for my use cases (limited use, limited need for changing models).

It is a pain from openRouter if you don't define your providers correctly, but for DeepSeek, surely not- the weights aren't released yet and there's only one provider, DeepSeek.

With Deepseek as the provider, there's no issue of course, but that means you don't filter providers for data retention, and you could also choose direct API use with them at that point.
Post reply on HN