DeepSeek V4 Pro 0813 • Hacker News Board

Re: DeepSeek V4 Pro 0813

#121

Post by npn » Wed, Aug 12, 2026, 6:32 PM UTC

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 for Deepseek Harness (yes it is the official name) release then try again.

for your kind of task, harness tools matter.

Re: DeepSeek V4 Pro 0813

#122

Post by freakynit » Wed, Aug 12, 2026, 6:35 PM UTC

shimman wrote: post #119

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 always wondered if I was using containers wrong because none of them I've ever had to create were complicated. Maybe it's because I choose tools that make local development easy (Go + sqlite + various CLTs) or maybe it's because I never hard to interact with this on the professional side outside of making images for our projects (which still weren't complicated for the reasons above). LLMs make containers in a p…

This was the repo: https://github.com/amalshaji/portr

And this was my gh issue: https://github.com/amalshaji/portr/issues/308

And below was my prompt:

""" give me single docker-compose file that i can run on my server to run current project... you can read README.md , and then, this relevant page: https://docs-custom-reverse-proxy.portr-docs.pages.dev/docs/... ... this was the result of me raising github issue: https://github.com/amalshaji/portr/issues/308 ... you can use gh cli to fetch the details and comments...

i already have a caddy server running on my vps... and i will create wildcard certificates myself using certbot.. the domain name will be helloportr.xyz ... also, ports up to 9019 are already taken...

ask me if anymore info is needed... """

You can try yourself and let me know of what you got.

Re: DeepSeek V4 Pro 0813

#123

Post by scrlk » Wed, Aug 12, 2026, 6:36 PM UTC

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…

What harness are you using? DS V4 is harness sensitive.

Re: DeepSeek V4 Pro 0813

#124

Post by freakynit » Wed, Aug 12, 2026, 6:37 PM UTC

scrlk wrote: post #123

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…

What harness are you using? DS V4 is harness sensitive.

Pi

Re: DeepSeek V4 Pro 0813

#125

Post by freakynit » Wed, Aug 12, 2026, 6:38 PM UTC

npn wrote: post #121

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 for Deepseek Harness (yes it is the official name) release then try again. for your kind of task, harness tools matter.

I used pi

Re: DeepSeek V4 Pro 0813

#126

Post by derangedHorse » Wed, Aug 12, 2026, 6:39 PM UTC

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.

Re: DeepSeek V4 Pro 0813

#127

Post by gkbrk » Wed, Aug 12, 2026, 6:40 PM UTC

npn wrote: post #121

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 for Deepseek Harness (yes it is the official name) release then try again. for your kind of task, harness tools matter.

If the model cannot figure out simple and ubiquitous tools, how is it supposed to figure out complex problems? All of the good models basically work with any harness, including giving them a single "shell command" tool. They can just figure things out.

Re: DeepSeek V4 Pro 0813

#128

Post by nozzlegear » Wed, Aug 12, 2026, 6:40 PM UTC

SV_BubbleTime wrote: post #107

nozzlegear wrote: post #76

Earlier quoted context omitted.

This but unironically

[flagged]

Is this bait?

> So.. flesh this out and don’t be a coward about it.

No.

Re: DeepSeek V4 Pro 0813

#129

Post by freakynit » Wed, Aug 12, 2026, 6:41 PM UTC

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.

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.

Re: DeepSeek V4 Pro 0813

#130

Post by spijdar » Wed, Aug 12, 2026, 6:42 PM UTC

svachalek wrote: post #91

goldenarm wrote: post #40

Earlier quoted context omitted.

Geometric mean of all these benchmarks : * GPT-5.6 Sol: 65.5 * Fable 5 (w/ fallback): 64.5 * Opus 5: 64.0 * DS-V4-Pro 0813: 62.5 * Kimi-K3: 62.3 * DS-V4-Flash 0731: 55.8 * GLM-5.2: 47.3

Maybe it's me but I don't see how DS Flash is better than GLM at all, much less by a huge gap. I'd probably protest less against Fable and Opus being put at the same level than many would, but there's no denying the two models are a very different experience from each other. I guess where I'm going is no one should pick a model by the benchmarks.

I'm not the most LLM-savvy person around, and I'm not gonna say I've put a ton of effort into practically compared these open models. But, a month or two ago I did do some "practical evaluates" testing GLM 5.2 versus DSv4 (flash/pro) with OpenCode's subscription with some late 80s Unix clone-type work, and this jives with my experience.

GLM ended up being far slower, and far more expensive, for approximately the same results. There was never a problem that GLM could solve that DS couldn't solve, faster, and significantly cheaper.

I strongly agree that you shouldn't pick a model based on benchmarks. But for me, I found GLM really underwhelming given its cost and speed.

DSv4 isn't as good as GPT or Claude or what have you, but it's fast, and pretty darned effective. I can run a 3-bit quant of DSv4 locally on my system with ~15 tokens per second, and for a local model it might be the most overall effective at coding. For what it is, it's extremely impressive.