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

131–140 of 493 posts

Re: DeepSeek V4 Pro 0813

#131

Post by lousken »

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.

Are we testing the model or the harness? If benchmarks show certain numbers it should perform as such without it

Re: DeepSeek V4 Pro 0813

#133

Post by hadlock »

gkbrk wrote: post #127
npn wrote: post #121

Earlier quoted context omitted.

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.

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

Re: DeepSeek V4 Pro 0813

#134

Post by sheeshkebab »

gkbrk wrote: post #127
npn wrote: post #121

Earlier quoted context omitted.

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.

This. The same goes for “skills”, skill type “subagents” and other bullshit - powerful models don’t need any of that anymore I noticed.

Re: DeepSeek V4 Pro 0813

#135

Post by azinman2 »

hadlock wrote: post #133
gkbrk wrote: post #127

Earlier quoted context omitted.

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.

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

Which works better for you?

Re: DeepSeek V4 Pro 0813

#137

Post by Myzura »

This model is not very good at coding, but it is quite good at research, evaluation and action, I don't write code, but it really goes head-to-head with the most expensive models in searches such as stock market and forex

Re: DeepSeek V4 Pro 0813

#138

Post by KronisLV »

hadlock wrote: post #133
gkbrk wrote: post #127

Earlier quoted context omitted.

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.

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.

Re: DeepSeek V4 Pro 0813

#139

Post by npn »

gkbrk wrote: post #127
npn wrote: post #121

Earlier quoted context omitted.

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.

I don't think so. there is a lot of tools with similar usage, some harness even bring their own internal tools for accurately manipulation.

also, even if some models claim that they have full 1M context window, some only work effective with the head or tail of the window, a proper harness tool will know about the limitation of the model and act accordingly.

then also the output format, the tool calling syntax, the quirks and gotchas of each model.

it is not simple as just throwing everything at the model, especially when your project has hundred of files or so.

Re: DeepSeek V4 Pro 0813

#140

Post by davidlt »

hadlock wrote: post #133
gkbrk wrote: post #127

Earlier quoted context omitted.

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.

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

I just wanted to emphasize this. Harness is a big part of how things perform thus usually it's harness + model co-design that's important.
Post reply on HN