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

231–240 of 493 posts

Re: DeepSeek V4 Pro 0813

#231

Post by celsoneto07 »

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…

I've been doing pretty heavy stuff with DeepSeek with a good degree of success. The thing is: I don't trust it to go fully autonomous. I check the steps, I steer it. For the pricing, it's worthy. Let's how the price increase is going to change my behavior.

Re: DeepSeek V4 Pro 0813

#232

Post by gpt5 »

computerex wrote: post #212
segmondy wrote: post #178

Earlier quoted context omitted.

you're thinking of one shot. if they are running an agentic loop then they don't need multiple passes. an agentic loop is multiple passes with tool calls and tools could fail and agent would correct from seeing the failure. a bad model will compound on error and fail, a good model will correct. 1 test is fine to gauge the quality of the model.

An agent doing a task even with multiple back to back calls like normal without an example is zero shot. An agent doing a task with 1 example is one shot. An agent doing a task with a few examples is few shot. I don't think you are correctly using these terms. The multiple back to back LLM calls are done on accumulating context, so if there is a sampling error it could throw the entire session out of whack, because L…

That's not true. An agent in a loop can test itself, review, verify and iterate as much as needed. That's one of the primary reasons more capable models tend to have a higher success rate.

I don't disagree that multiple tests increase confidence, but it's not correct to argue that an agent in a loop harness is equivalent to oneshotting

Re: DeepSeek V4 Pro 0813

#233

Post by smb06 »

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?

My company pretty much exclusively uses Sol and Luna

Re: DeepSeek V4 Pro 0813

#235

Post by ericfr11 »

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...

I am still on Opus 4.8, with a custom built harness and it works very well even on multi-repos, across stack, deep changes. I also have a very solid test suite which is helping the coding agent a lot

Re: DeepSeek V4 Pro 0813

#236

Post by ericfr11 »

sejje wrote: post #228
mixedCase wrote: post #179

Earlier quoted context omitted.

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.

Same for me, with Claude Opus/Sonnet. All the models are almost equivalent if well steered

Re: DeepSeek V4 Pro 0813

#237

Post by akman »

vrganj wrote: post #222
akman wrote: post #190

Earlier quoted context omitted.

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…

As far as AI is concerned, it looks like you will need to pick 1?

Re: DeepSeek V4 Pro 0813

#238

Post by ericfr11 »

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…

Harness is the key. I built my own to "talk" our institutional knowledge and it's working great

Re: DeepSeek V4 Pro 0813

#239

Post by apitman »

miohtama wrote: post #225
apitman wrote: post #171

Earlier quoted context omitted.

Wait people use terra?

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.

Re: DeepSeek V4 Pro 0813

#240

Post by akman »

Eueudhsbsj32 wrote: post #215
akman wrote: post #190

Earlier quoted context omitted.

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".

So is your concern more about reducing the risk of an authoritarian China "winning" the AI race? And less about reducing the risk of your data being used against you personally? To me, the risks of an individual helping China to continue to develop their AI by being a customer is pretty marginal compared with the personal risks of my data being used against me.

I see. Though if you follow the argument set forth by Dario, it seems you'll not only have your concern to worry about (i.e., personal risks of your data used against you), but many more as well on top of that.
Post reply on HN