It's probably good, and the best for Deepseek models, but do we really need one harness per model?
DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost
181–190 of 325 posts
Re: DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost
#182It's pretty funny, i'm a $200/m Claude subscriber and i've had little need to use anything else. However the more Claude has been restricting my workflow (notably around the recent IDE/-p usage change) the more i've been wanting to go elsehwere. I'm concerned since i really want SOTA reasoning, but DeepSeek still has me interested.
I gave a fairly complex reverse engineering task to DS-4 xhigh and GPT-5.5 xhigh today. After about 6 hours, both ultimately failed to fully RE, however, there were some drastic differences: DS stopped every 30 minutes or so, saying it did full RE and it should all work now, while in fact, it didn't complete even 1% of it. It also looked for shortcuts again and again, despite me prompting heavily that the specific sh…
> DS stopped every 30 minutes or so, saying it did full RE and it should all work now, while in fact, it didn't complete even 1% of it. It also looked for shortcuts again and again, despite me prompting heavily that the specific shortcut may not be used. It was a complete and utter failure.
This is my experience with non-SOTA models across the board. When you try them on little tasks and they work it feels amazing, but then you go deeper and you're back to going in loops and fighting the model for hours.
Switching back to a SOTA model immediately yields progress again.
When I read all of the comments from people saying they can't tell a difference between Opus and I don't know if they haven't really used it much yet, or if they're just not doing anything complicated.
Re: DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost
#183I'm not sure you need a "DeepSeek native coding agent" to take advantage of DeepSeeks cache, yesterday as the Codex quota usage issue still wasn't solved for me, I wrote a tiny little bridge so I could use DeepSeek V4 Pro via Codex, and seems most of everything I did was basically cached as far as I can tell: https://i.imgur.com/7eKn6wN.png (2026-05-23 Input (Cache hit): 39,123,200 tokens, Input (Cache miss) 1,692,28…
> I wrote a tiny little bridge so I could use DeepSeek V4 Pro via Codex Can you share the bridge. DeepSeek v4 is awesome paired with claude-code or opencode. I found that claude code costs me less than opencode and I am presuming this is due to a better engineered harness.
Claude code and open code are streaming piles of shit
Re: DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost
#184Earlier quoted context omitted.
out of curiosity, how do you measure cache hit rate in opencode ?
opencode stats
So the calculation is:
Total input token = input + cache read + cache write Cache hit rate = cache read / total input token.
That is 71% in my very limited use of opencode.
Re: DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost
#185Earlier quoted context omitted.
I'd generally agree about Deepseek being as good as Sonnet - but I have extreme trouble with prompt compliance with V4 Pro in a way that I've never had with Sonnet. I'll tell it "find the bug, but don't fix it" or "please use this tool I just developed" and it'll ignore me a high fraction of the time. It's bad enough that I'm working on guardrails at the harness level because prompting appears to be useless. Do you h…
I have Opus make a fairly detailed plan, then Deepseek implements, and GPT reviews. With that setup, I have zero issues, probably because what you mention is handled (the plan keeps it on track and the reviewer catches any issues). Now that you mention it, though, I have seen it do a few things that weren't in the plan. The reviewer caught them, though, so they didn't cause a problem, and it's so cheap that overall i…
Which CLIs are you using for each of the steps?
Re: DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost
#186Earlier quoted context omitted.
I have Opus make a fairly detailed plan, then Deepseek implements, and GPT reviews. With that setup, I have zero issues, probably because what you mention is handled (the plan keeps it on track and the reviewer catches any issues). Now that you mention it, though, I have seen it do a few things that weren't in the plan. The reviewer caught them, though, so they didn't cause a problem, and it's so cheap that overall i…
Which CLIs are you using for each of the steps?
OpenCode for everything: https://www.stavros.io/posts/how-i-write-software-with-llms/
Re: DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost
#187This is not an agent by DeepSeek, so the title is misleading.
Re: DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost
#188Well folks here we have it: DeepSeek’s brand is now strong enough people want to jump on their brand recognition.
Re: DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost
#189Earlier quoted context omitted.
I am getting 98.6% cache hit ratio on deepseek-v4-flash with opencode
That’s impressive! On the sheer performance it’s comparable to Opus ?
Here are my stats (from DeepSeek directly, with a script I wrote). The prices are what equivalent Sonnet usage would have cost, the actual amount I paid was $10. On performance, DeepSeek V4 Pro is comparable to Sonnet for me.
./cost.py amount-2026-5.csv 0.3 3.75 15
input_cache_hit_tokens: 472,971,520 tokens -> $141.8915
input_cache_miss_tokens: 13,299,013 tokens -> $49.8713
output_tokens: 3,334,962 tokens -> $50.0244
cache hit rate: 97.27% (472,971,520/486,270,533)
cache miss rate: 2.73% (13,299,013/486,270,533)
total: $241.7872
Re: DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost
#190Quite interesting being Terminal based and the AI skills staying within a file of it's own.
Will give a go and see how cache behaves