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

351–360 of 493 posts

Re: DeepSeek V4 Pro 0813

#351

Post by sebastiennight »

hgoel wrote: post #105
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.

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.

This is a "load-bearing" issue recently.

I think the idea is packing more information into fewer words, but the result is a word salad that is somehow simultaneously very dense in adjectives and adverbs, and still way too verbose.

Re: DeepSeek V4 Pro 0813

#352

Post by polynomial »

simonw wrote: post #136

Nice bicycle chain, the little basket with a fish didn't show up in the right place: https://tools.simonwillison.net/markdown-svg-renderer#url=ht...

Honestly they should all use their respective pelicans as their logos. Or maybe a browser plugin to do do that on the Hugging Face and OpenRouter sites.

Re: DeepSeek V4 Pro 0813

#353

Post by pmontra »

scrollop wrote: post #350
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.

If you read the many, many complaints about opus 5 on anthropic forums, the sentiment is that opus 5 output is poor and people are back to 4.8 and 4.6. You may want to re-evaluate and compare to the older models.

Opus 5 is too verbose.

I'm using Sonnet 5 on a large porting project and it's good. I switched from Opus 5 to Sonnet 5 on a project of another customer and I didn't notice a decrease in quality. I concede that it's very difficult to assess a difference in quality unless one uses both models on the same task and carefully compare the code, not the output in the terminal. I really don't have the time and the tokens for that. Anyway, Sonnet is still doing a good job.

Re: DeepSeek V4 Pro 0813

#354

Post by laichzeit0 »

fooblaster wrote: post #332
eru wrote: post #320

Earlier quoted context omitted.

(Not the original commenter.) You can rack up quite a lot of tokens if you ask it to try out a lot of things, eg for performance investigations and trying out optimisation ideas.

is there a standard pattern for this? Like spawn an agent for each technique to try?

I regularly do a “go to DynaTrace, look at how this service gets used in production then use a profiler and see if there’s any low hanging optimisations we could make” on stuff. LLMs are really good at doing everything that was fun about software development.

Re: DeepSeek V4 Pro 0813

#355

Post by sebastiennight »

sejje wrote: post #282
gnunez wrote: post #262

Earlier quoted context omitted.

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?

I think people are wrapping that across the English language. In English, these two tasks are exactly the same: "Would you hand me that item?" "Please hand me that item" But when posed to the LLM, they generate different outputs. One character difference in the prompt might be a whole different output. People who aren't programmers mostly don't know that there's any difference. They asked for the same thing, it knows…

Not to be too pedantic, but these requests would not be exactly the same.

There is a bit of indexicality in "Would you hand me that item ?"

that might cause it to be interpreted as an actual question rather than a request, and might elicit different responses:

- maybe _I_ would not hand this to you (I'm busy right now), but the person next to me whose hands are free would, so I'd nod to them. However, if you had said "Please hand me that item" I'd put down what I was doing to comply.

- maybe I would not hand _this_ to you (it's not the right tool IMO), but I'd suggest another option. However, if you had said "Please hand me that item" I'd put my doubts aside to comply.

- maybe I would not hand this to _you_ (you're not the one who should be handling it), but I'd do the thing myself or hand it to a more qualified member of the group. However, if you had said "Please hand me that item" I'd trust you enough to comply.

I think this distinction is relevant in that I've found people to sometimes have difficulties understanding how similar LLM prompting is to giving instructions to human colleagues.

I've had a collaborator who though very highly of his own prompting skills (while his prompts were very ambiguous and of the "make no mistakes, erase everything & correct yourself if you find one" variety) and blamed the models for not being "smart enough", and it was very noticeable that his management style for the juniors on his team was similarly unproductive.

Re: DeepSeek V4 Pro 0813

#356

Post by irthomasthomas »

p1necone wrote: post #312
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).

This has not been my experience. Generally I do pin to 1 provider, or 1 provider with a couple fallbacks (especially with deepseek - most providers are 10x the cached token price compared to deepseek themselves), but even when I don't I still usually see 99%+ cache hit percentage. Specifically using pi with various ad-hoc customisations (that I was careful not to break prompt caching with).

then what is the point of using operouter for this model? Just use the deepseek API and save the 5% fee on top of the better caching rate.

Re: DeepSeek V4 Pro 0813

#359

Post by miohtama »

apitman wrote: post #239
miohtama wrote: post #225

Earlier quoted context omitted.

I use mostly Terra. Much better than Opus 5. Much more token mileage.

But why? Luna Max is almost the same intelligence as Terra xhigh and way way cheaper. And Terra max is almost the same as Sol high. I just don't really see a place for Terra but slower.

This is a good tip. I will try. Thank you!

Re: DeepSeek V4 Pro 0813

#360

Post by eru »

laichzeit0 wrote: post #354
fooblaster wrote: post #332

Earlier quoted context omitted.

is there a standard pattern for this? Like spawn an agent for each technique to try?

I regularly do a “go to DynaTrace, look at how this service gets used in production then use a profiler and see if there’s any low hanging optimisations we could make” on stuff. LLMs are really good at doing everything that was fun about software development.

Ha, I have a whole hobby work-stream going on about finding low-hanging fruit in various open source projects to turn into valuable contributions.

Two premier sources: (1) look at good contributions someone already tried to make, but that got stuck in review or were otherwise abandoned. (2) look at user reported bugs and see if we can find a user reported bugs, and see if we can reproduce and fix cheaply.

Both are explicitly scoped as best-effort affairs: move on, if you can't quickly make progress.

Most of the work I have to do as a human is review and navigating the submission process: tokens are cheap these days, so you really need to make sure the contribution is actually worth someone's time to review.

Post reply on HN