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

221–230 of 493 posts

Re: DeepSeek V4 Pro 0813

#221

Post by dominotw »

KronisLV wrote: post #138
hadlock wrote: post #133

Earlier quoted context omitted.

When it comes to quality of outcome, since at least Feburary, the harness has almost equal, if not more weight than the model itself. It's no longer "which model is the best?" it's "which model + harness is the best?" I get drastically different tool call failure rates using Claude SDK vs OpenCode using Qwen 3.6 models

> the harness has almost equal, if not more weight than the model itself This feels like a horrible failing of the models to generalize, then - both basic and intermediate tasks should be possible to do with Claude Code, OpenCode, Pi, ZCode, Kimi Code, Dirac and tbh any other mainstream or even slightly niche harness. Not doubting the claim itself, there's a reason why good benchmarks include the harness.

i think thats BS that harness has equal weight. most of intellegice is still coming from training data not from RL. so how is 'coevolved harness' equal weight.

Re: DeepSeek V4 Pro 0813

#222

Post by vrganj »

akman wrote: post #190
Eueudhsbsj32 wrote: post #79

Earlier quoted context omitted.

Unless you're Chinese, why would you care if they see your data? As an American, I'd much rather have my data kept outside the country than here where companies and the government have a lot more leverage over me.

I do think this question comes up a lot-- I can understand why. For some well-explained reasons, check out https://darioamodei.com/essay/the-adolescence-of-technology and search for "CCP".

As somebody from neither the US nor China, this argument would be much stronger if the US hadn't started acting like a rogue state - starting wars of aggression and messing up the world's energy supply, actively speeding up climate change, kidnapping leaders of sovereign nations, threatening its allies (!) with invasion, etc etc.

The CCP's not great either, sure. But the Americans don't really have a leg to stand on anymore.

Re: DeepSeek V4 Pro 0813

#223

Post by simonw »

throwaway9af11m wrote: post #220
simonw wrote: post #153

Earlier quoted context omitted.

Default effort for OpenRouter. I'll try a grid of efforts... Wow, the low, medium, and high pelicans came out in surprisingly different styles: https://tools.simonwillison.net/markdown-svg-renderer#url=ht...

[flagged]

If I live my life on the basis that some people don't share my sense of humor, and hence I should avoid doing anything funny that might be misunderstood, my life will be a lot less fun.

Re: DeepSeek V4 Pro 0813

#224

Post by miohtama »

Foobar8568 wrote: post #147
freakynit wrote: post #129

Earlier quoted context omitted.

Depends on project complexity. For one of my more complex projects, I exclusively use sol-high ... nothing below that works correctly. For this however, a comparatively much simpler task, tarra-high works fine.

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.

Re: DeepSeek V4 Pro 0813

#225

Post by miohtama »

apitman wrote: post #171
freakynit wrote: post #108

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. The…

Wait people use terra?

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

Re: DeepSeek V4 Pro 0813

#226

Post by hgoel »

greenchair wrote: post #213
hgoel wrote: post #105

Earlier quoted context omitted.

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.

yep, it is so bad i had to create rules to cut down on the techbro language and domain slang.

I just canceled my Claude subscription outright. The models are all gairly fungible, it's easy enough to just switch to another provider.

Re: DeepSeek V4 Pro 0813

#227

Post by Art9681 »

derangedHorse wrote: post #126
freakynit wrote: post #108

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. The…

Terra has not been able to do any of the technical tasks I've asked of it correctly. I'm surprised others get use out of it. Anything below Sol high tends to give me mostly unreliable results. I'm using codex as my main harness but maybe it performs better with a different one.

Terra is great. It's wild how different our experiences are.

Install the Superpowers plugin.

Behold.

Re: DeepSeek V4 Pro 0813

#228

Post by sejje »

mixedCase wrote: post #179
derangedHorse wrote: post #126

Earlier quoted context omitted.

Terra has not been able to do any of the technical tasks I've asked of it correctly. I'm surprised others get use out of it. Anything below Sol high tends to give me mostly unreliable results. I'm using codex as my main harness but maybe it performs better with a different one.

With Pi as a harness I've been using OpenAI models as a worker with an Opus 5 (in Claude Code) planner. I've only had a few issues with Terra High/Medium and absolutely none with Sol Medium+ on a fairly complex Rust project that targets Linux, Mac, Windows and Web, with plenty of nasty FFI, VMs, remotely debugging systems, among some other things within a monorepo. I think the key is to give them a nice assortment of…

Plan with sol-med, implement with luna-high. Rarely a problem.

Re: DeepSeek V4 Pro 0813

#229

Post by almyk »

moritzwarhier wrote: post #214

Is having padded version numbers with a leading zero a common thing? Wondering, sorry if it's a dumb triviality to ask. Is this even a (sub-)version number? I mean the major version is clearly 4.

It is the date of the release
Post reply on HN