Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

DeepClaude – Claude Code agent loop with DeepSeek V4 Pro

github.com

Post reply on HN
Print view View original

201–210 of 322 posts

Re: DeepClaude – Claude Code agent loop with DeepSeek V4 Pro

#201

Post by dandaka »

syntex wrote: post #180

Not sure you can replace Claude with DeepSeek V4 that easily and have same results. From what I see while building my own agentic system in Elixir, the problem is in training for your specific harness/contracts. Claude/GPT-style models seem to be trained around very specific contracts used by the harness like tool call formats, planning structure, patching, reading files, recovering from errors, and knowing when to s…

I hope they collaborate with open source harness providers (Pi, Opencode) and train models with those. So next generations will have better integration and better overall quality.

Re: DeepClaude – Claude Code agent loop with DeepSeek V4 Pro

#202

Post by DeathArrow »

wizhi wrote: post #157
DeathArrow wrote: post #145

Earlier quoted context omitted.

>If you're looking for Claude Code alternatives, I would first suggest looking into pi.dev or opencode for your harness. While those are nice, Claude Code has the largest amount of plugins and skills I want to use.

Aren't skills just literal plaintext files? Why not just copy them?

Yes, they are .md files but they can rely on builtin behaviors in the harness or on plugins.

Re: DeepClaude – Claude Code agent loop with DeepSeek V4 Pro

#204

Post by karel-3d »

zozbot234 wrote: post #186
karel-3d wrote: post #183

Can I... somehow run this locally? DeepSeek is opensource? Do I even need their API key? (I have no experience with running anything locally, maybe it's a stupid question)

Waiting for official support in llama.cpp. There is a fork that can run a lightly quantized (Q2 expert layers) DeepSeek V4 Flash in 128GB RAM without offloading weight fetches from disk.

Ouch. Can't run that on my M4 mac with 48GB RAM.

Re: DeepClaude – Claude Code agent loop with DeepSeek V4 Pro

#205

Post by lhl »

rapind wrote: post #96
aftbit wrote: post #21

#!/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…

For those that don't want their data trained on, OpenRouter allows you to have account-wide or per-request routing with either provider.data_collection: "deny" or zdr: true (zero data retention).

Also, you can use HuggingFace Inference for DeepSeek V4 or Kimi K2.6, both of which work quite well and route through providers that you can enable/disable (like Together AI, DeepInfra, etc) - you'll have to check their policies but I think most of those commercial inference providers claim to not train on your data either.

Re: DeepClaude – Claude Code agent loop with DeepSeek V4 Pro

#206

Post by energy123 »

cpursley wrote: post #195
energy123 wrote: post #104

Earlier quoted context omitted.

It's not even that much cheaper, GPT 5.5 is about 2x more expensive per task than Deepseek v4 Pro when you adjust for less token usage, according to Artificial Analysis. Doesn't seem worth it to me.

Are we talking pay as you go API or vs plans?

Pay as you go API rates.

Re: DeepClaude – Claude Code agent loop with DeepSeek V4 Pro

#208

Post by vidarh »

maxgashkov wrote: post #200
rapind wrote: post #96

Earlier quoted context omitted.

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…

As of now, OpenRouter offers multiple providers for DeepSeek with ZDR (not sure if they respect it but still).

At several times the price of DeepSeek, though, so it's a tradeoff... Even then Pro is still cheaper than Haiku.

Re: DeepClaude – Claude Code agent loop with DeepSeek V4 Pro

#210

Post by miroljub »

lhl wrote: post #205
rapind wrote: post #96

Earlier quoted context omitted.

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…

For those that don't want their data trained on, OpenRouter allows you to have account-wide or per-request routing with either provider.data_collection: "deny" or zdr: true (zero data retention). Also, you can use HuggingFace Inference for DeepSeek V4 or Kimi K2.6, both of which work quite well and route through providers that you can enable/disable (like Together AI, DeepInfra, etc) - you'll have to check their poli…

I wonder why the question about data security and training comes often with DeepSeek, Kimi, Glm and never with Anthropic, OpenAI, and Google models.

Why is that?

IIRC, USA data protection protects data of US citizens only, foreigners data is not protected, and the companies are not even allowed to disclose when they collect those data.

Post reply on HN