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

131–140 of 322 posts

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

#131

Post by Culonavirus »

_345 wrote: post #9

If 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

We're not yet at a point of saturation when all the frontier models would be of somewhat comparable "intelligence" and we could decide which to use based on other factors (speed, effective context window etc.), so I honestly don't see why would you (as a company or an employee) not use the best available model with the highest (or at least second highest) thinking effort. The fees are not exactly cheap, but not that expensive either.

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

#132

Post by DetroitThrow »

skeledrew wrote: post #111
bakugo wrote: post #65

Earlier quoted context omitted.

> 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.

They have a pretty decent explanation. https://github.com/badlogic/pi-mono/blob/main/CONTRIBUTING.m...

"Decent" is doing some work. This is going beyond any norms I've encountered in OSS to close issues by default via a LLM or an "issue holiday".

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

#133

Post by groestl »

otabdeveloper4 wrote: post #128
yard2010 wrote: post #125

Earlier quoted context omitted.

How come such slop is allowed here, what value do these vibe coded zero shot "projects" add? Why not just post the prompt?

Recruiters used to use the candidate's Github "sources" page for evaluating candidates as a kind of proof-of-work.

And recruiter agents still do.

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

#134

Post by fragmede »

yard2010 wrote: post #125
varenc wrote: post #119

Earlier quoted context omitted.

The more interesting part of deepclaude is the local proxy it runs to switch models mid-session and do combined cost tracking. Though these features seem quite buried in the LLM-generated readme. Looking at the history, it appears they were added later, and the readme wasn't restructured to highlight this. Also, the author checked in their apparently effective social media advertising plan: https://github.com/aattara…

How come such slop is allowed here, what value do these vibe coded zero shot "projects" add? Why not just post the prompt?

Convenience? Am I supposed to take the prompt and use my own tokens on it? Why should I have to do that?

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

#135

Post by taocoyote »

wolttam wrote: post #53
justech wrote: post #30

If 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’m going to throw my harness in the ring: https://codeberg.org/mlow/lmcli

Looks interesting. Does it offer anything special that pi.dev or opencode does not?

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

#136

Post by adonese »

faangguyindia wrote: post #100
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 $@

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

I tried it on a non trivial, but also well documented and self contained task. It did amazingly well. I used deepseek v4 pro via deepseek platform. The model is very fast and also it is super cheap. I burned only 0.06 USD (I reckon how the same task would have cost me had I used e.g., amp).

PS. mentioning amp because i used to use it and I pay directly for token. I topped up 5 usd so I will be going to use it and see how far can it take me. But my impression so far is even when model subsidization is done, those open source models are quite viable alternatives.

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

#137

Post by wolttam »

taocoyote wrote: post #135
wolttam wrote: post #53

Earlier quoted context omitted.

I’m going to throw my harness in the ring: https://codeberg.org/mlow/lmcli

Looks interesting. Does it offer anything special that pi.dev or opencode does not?

Probably not, `lmcli` is very lean. I would consider it a slightly lower-level tool than either pi.dev or opencode. E.g. there is no built-in coding agent, but it's easy to build one up in the config with your own prompt (or use the example).

It's proven useful for me, and I figure others might appreciate how light of a shim it is between you and the models.

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

#139

Post by dev_hugepages »

2ndorderthought wrote: post #16
vitaflo wrote: post #13

I'm not exactly sure what the point of this is. Deepseek already has instructions to use its API with many CLI's including Claude Code directly: https://api-docs.deepseek.com/quick_start/agent_integrations...

There probably isn't a point. Someone didn't understand something, didn't research it, so they 1 shotted their first thought and sent it to the front page of HN and all of their socials. It's the future bruh

And now, because we all upvoted and commented on it, the vibe coded slop of the new user is on the front page now.
Post reply on HN