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

141–150 of 322 posts

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

#141

Post by zozbot234 »

adonese wrote: post #136
faangguyindia wrote: post #100

Earlier quoted context omitted.

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…

> But my impression so far is even when model subsidization is done, those open source models are quite viable alternatives.

My understanding is that DeepSeek V4 Pro is going to be uniquely good at working on consumer platforms with SSD offload, due to its extremely lean KV cache. Even if you only have a slow consumer platform, you should be able to just let it grind on a huge batch of tasks in parallel entirely unattended, and wake up later to a finished job.

AIUI, people are even experimenting with offloading the KV cache itself to storage, which may unlock this batching capability even beyond physical RAM limits as contexts grow. (This used to be considered a bad idea with bulky KV caches, due to concerns about wearout and performance, but the much leaner KV cache of DeepSeek V4 changes the picture quite radically.)

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

#142

Post by nyssos »

Culonavirus wrote: post #131
_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…

Agreed that we're not at saturation, but we don't have a canonical "best" either. For example ChatGPT 5.5 + Codex is, in my experience, vastly superior to Opus 4.7 + Claude Code at sufficiently well-specified Haskell, but equally vastly inferior at correctly inferring my intent. Deepseek may well have its own niche, though I haven't used it enough to guess what it might be.

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

#143

Post by JSR_FDED »

maxdo wrote: post #97
_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

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: >Includ…

I'd argue that you need the model that's good enough, not the best.

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

#144

Post by Alifatisk »

girvo wrote: post #59
2ndorderthought wrote: post #18

Earlier quoted context omitted.

How is glm 5.1? I have t tried it yet but have been meaning too

It's surprisingly good. Beats MiniMax 2.7 and Qwen 3.5 Plus in my testing (I haven't tested 3.6 plus though), quite handily. It's far better than Sonnet, and often equivalent to Opus for the web development and OCaml tasks I'm using it for. It definitely isn't Opus 4.7, but its far good enough to earn it's keep and is substantially cheaper.

I second this, glm-5.1 is incredible.

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

#145

Post by DeathArrow »

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

>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.

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

#146

Post by incrudible »

2ndorderthought wrote: post #73
croes wrote: post #50

Earlier quoted context omitted.

From vibe coders for vibe coders

I don't always copy paste vibe coded project readme mds into Claude code and ask them to rewrite it but when I do... actually that's all I do now because my goal in life is to make wealthy overvalued companies wealthier.

Anthropic is the opposite of wealthy, the more you use their service, the more money they lose. Unless you think your precious MDs being used for training data is gonna make them rich eventually.

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

#147

Post by oefrha »

mikeocool wrote: post #107
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.

Their process is outlined here: https://github.com/badlogic/pi-mono/blob/main/CONTRIBUTING.m... > Maintainers review auto-closed issues daily and reopen worthwhile ones. Issues that do not meet the quality bar below will not be reopened or receive a reply. Seems like not an unreasonable way to deal with the problem of large numbers of low quality issues being submitted.

If that process actually happens then there’s absolutely no reason not to have the reviewing maintainer close it after review instead. The only reasonable conclusion is that documented process is aspirational at best and vibed itself at worst.

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

#148

Post by adonese »

zozbot234 wrote: post #141
adonese wrote: post #136

Earlier quoted context omitted.

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…

> But my impression so far is even when model subsidization is done, those open source models are quite viable alternatives. My understanding is that DeepSeek V4 Pro is going to be uniquely good at working on consumer platforms with SSD offload, due to its extremely lean KV cache. Even if you only have a slow consumer platform, you should be able to just let it grind on a huge batch of tasks in parallel entirely unat…

Is there any place I can read about KV? Excuse my ignorance as I'm not familiar with this topic and I read scattered notes that deepseek's cost are well optimized due to how their kv cache work. But I want to read more how kv cache relates to the inference stack and where does it actually sit.

> AIUI, people are even experimenting with offloading the KV cache itself to storage, which may unlock this batching capability even beyond physical RAM limits as contexts grow.

Especially this point. Any reason that this idea was considered bad? Is it due to the speed difference between the GPU VRAM to the RAM?

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

#149

Post by tariky »

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…

I wanted to try this. To bring back opus and sonnet do I just reset those env's?

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

#150

Post by heisenbit »

nadermx wrote: post #29
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 $@

The AI wars have begun

And they are enticing human agents to further their agendas using techniques learned from the white mice.
Post reply on HN