Is claude code the best coding harness? Anyone running evals on that?
DeepClaude – Claude Code agent loop with DeepSeek V4 Pro
91–100 of 322 posts
Re: DeepClaude – Claude Code agent loop with DeepSeek V4 Pro
#92Is claude code the best coding harness? Anyone running evals on that?
In my anecdotal experience, it is not. Same model, opus, works better in 3P harnesses such as Factory Droid or Amp.
Claude code, on the other hand, is the most subsidized one, both for consumers (through max subscription) and for enterprises (token discounts). It is also heavily optimized for cost, specially token caching and reduced thinking, at the expense of quality.
Re: DeepClaude – Claude Code agent loop with DeepSeek V4 Pro
#93anthropic messed up big time harness works with any muh commodity LLM, meanwhile VCs were duped on the myth of FOOM AGI, probably not a cooincidence Anthropic is enmeshed with the scifi fan fic forum known as lesswrong. The world wants useful tools. The bay area bubble in contrast thrives on Mythos.
> anthropic messed up big time harness works with any muh commodity LLM
that surprised me too. The intelligence is at the client, and by making that open, anthropic has commoditized the coding agent.
Re: DeepClaude – Claude Code agent loop with DeepSeek V4 Pro
#94Earlier quoted context omitted.
What hardware are you using to power this?
> DGX Spark-alike Probably wasn't clear enough if you don't know what that is already, apologies It's an Asus Ascent GX10, which is a little mini PC with 128GB of LPDDR5X as shared memory for an Nvidia GB10 "Blackwell" (kind of, it's a long story) GPU and a MediaTek ARM CPU
pulls up chair
could you tell me the long story?
edit: or wait, is it quasi-Blackwell the way all DGX Sparks are quasi-Blackwell? like the actual silicon is different but it's sorta Blackwell-shaped?
Re: DeepClaude – Claude Code agent loop with DeepSeek V4 Pro
#95Earlier quoted context omitted.
I keep re-learning this lesson: I chug along with a lesser model then throw a problem at it that's too complex. Then I try different models until I give up and bring in Opus 4.6 to clean up.
And I keep using Opus to like, make git commits. Really just need a smart router that is actually smart, vs having to micromanage model
the problem is managing the contexts. your session might fit in Opus, but will that smaller model you dispatch the git commit to fit? even so, will it eat too much on prefill? do you keep compactions around for this, or RAG before dispatch or something? how do you button back up the response?
all doable but all vaguely squishy and nuanced problems operationally. kinda like harness design in general.
Re: DeepClaude – Claude Code agent loop with DeepSeek V4 Pro
#96#!/bin/sh export ANTHROPIC_BASE_URL=https://api.deepseek.com/anthropic export ANTHROPIC_AUTH_TOKEN=sk-secret export ANTHROPIC_MODEL=deepseek-v4-flash export CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1 exec claude $@
ANTHROPIC_MODEL=deepseek-v4-pro[1m]
ANTHROPIC_SUBAGENT_MODEL=deepseek-v4-flash
This is what I’ve been using for non-confidential projects for about a week now (soon after v4 came out). I honestly can’t tell the difference, but I’m not doing anything crazy with it either.
Worth noting that I don’t think DeepSeek‘s API lets you opt out of training. Once this is up on other providers though… (OpenRouter is just proxying to DeepSeek atm)
Re: DeepClaude – Claude Code agent loop with DeepSeek V4 Pro
#97If you're okay with sonnet level performance, this sounds like a straight upgrade. But I find that sonnet messes up too much, that it ends up not being worth cost optimizing down to using it or another sonnet-level model. Glad to have this as an option though
This is the problem: you need the best model, not just a good one, for:
- Good architecture, which requires reading specs, code, etc. reads like: lots of tokens in/out
- Bug fixing — same, plus logs, e.g. datadog
Once you've found the path, patches are trivial and the savings are tiny unless you're doing refactoring/cleanup.
testing gets more and more complicated. Take a look at opencode go, and you see this:
>Includes GLM-5.1, GLM-5, Kimi K2.5, Kimi K2.6, MiMo-V2-Pro, MiMo-V2-Omni, MiMo->V2.5-Pro, MiMo-V2.5, Qwen3.5 Plus, Qwen3.6 Plus, MiniMax M2.5, MiniMax M2.7, >DeepSeek V4 Pro, and DeepSeek V4 Flash
and now on your own with bugs, all of these models can produce at scale. Am i missing anything in this picture. What is the real use of cheaper models?
Re: DeepClaude – Claude Code agent loop with DeepSeek V4 Pro
#98Is there some way to make claude/codex beep when it finishes a task.
Re: DeepClaude – Claude Code agent loop with DeepSeek V4 Pro
#99If you're looking for Claude Code alternatives, I would first suggest looking into pi.dev or opencode for your harness. And then for models, you can choose from OpenCode Go (IMO most cost effect at this moment), OpenRouter, or direct from DeepSeek. Better if you go the Kimi route IMO and just buy a subscription from kimi.com
> I would first suggest looking into pi.dev Looked into this one. Thought it was suspicious that it only had 7 open issues on github. Turns out they have a bot that auto-closes every single issue just because. I honestly have no words.
The maintainer, Mario, sometimes declares the repo is on an “issue holiday” where issues are auto closed. This particular holiday is because there is a big refactor coming up. In non holiday periods issues can be reported as normal.
Re: DeepClaude – Claude Code agent loop with DeepSeek V4 Pro
#100#!/bin/sh export ANTHROPIC_BASE_URL=https://api.deepseek.com/anthropic export ANTHROPIC_AUTH_TOKEN=sk-secret export ANTHROPIC_MODEL=deepseek-v4-flash export CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1 exec claude $@
those who use deepseek v4, what level of output you get? Codex 5.3 or GPT 5.4?
is flash version on level of gpt 5.4 mini