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

DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost

esengine.github.io

Post reply on HN
Print view View original

111–120 of 325 posts

Re: DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost

#111

Post by franknord23 »

criemen wrote: post #74
nolok wrote: post #65

Earlier quoted context omitted.

> That'd be really easy to spot and also fix, most likely Ah, reminds me of good old "There are only 2 hard problems in computer science: cache invalidation, naming things, and off-by-1 errors."

> Ah, reminds me of good old "There are only 2 hard problems in computer science: cache invalidation, naming things, and off-by-1 errors." You quip, but LLM KV caching (from the harness side) is quite easy: You get a cache hit on stable prompt prefixes, period. That means you want to keep the prefix stable, and only append at the end of the conversation. Made up example: Don't put the git branch name into the system…

That sounds like the experience of writing Containerfiles; since steps are cached you want to pull the thing you are iterating on as far down as possible.

Re: DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost

#114

Post by tontinton »

embedding-shape wrote: post #2

I'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…

Yep exactly my thoughts, went and looked at the code for the deepseek provider in my coding agent. and basically all of what the author wrote there is implemented... http://github.com/tontinton/maki for the curios

Re: DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost

#115

Post by chuckadams »

droidjj wrote: post #110
m101 wrote: post #100

For those of you that use deepseek v4 occasionally, what harness do you use it with? I’m only familiar with claude code and codex. Any comments on what you can or cannot rely on it for relative to cc and codex would be appreciated too!

Check out pi.dev. OpenCode is a nice batteries-included Claude Code replacement, but I’m in love with the extensibility of Pi.

Any Pi extensions you'd specifically recommend? I'm just starting out with Pi, but I've had mixed results with extensions. I'm using Pi with gemma4 26b locally, so anything that's friendly to small local models would be appreciated. I think the only extension I'm using right now is pi-total-recall.

Re: DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost

#117

Post by throw10920 »

canadiantim wrote: post #4

So what's best low cost coding agent these days? Kimi 2.6? Qwen's latest closed model? Composer 2.5? DeepSeek?

Cursor with Composer 2.5 seems to be competitive with frontier models (Opus and GPT-5.5) for a significant price discount. Benchmarks are gamed, as always, but $0.55/task vs $11.02 a task definitely indicates that there's some cost advantage.

https://cursor.com/evals

Re: DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost

#118

Post by nextaccountic »

> Tool-call repair

> Tool arguments the model produces occasionally have JSON typos, unclosed quotes, or shape mismatches. Reasonix runs a schema-aware repair pass before dispatch so malformed args still execute.

So Deepseek API doesn't have a structured output option where you give a grammar and the model promises the output will follow this grammar?

Or it does, but it's buggy?

Re: DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost

#119

Post by unshavedyak »

logicchains wrote: post #85
unshavedyak wrote: post #49

It'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.

If you want SOTA reasoning you should be using GPT 5.5 Pro.

This is fair, but i've found the different models to have different moods and require different interactions to get them to stick to just the specific edits i ask for, etc.

I used to surf the three big players frequently and got really tired of the effort needed to steer some models. In the end i ended up sticking with Claude because it required less steering effort. While not strictly reasoning, a models ability to follow clear directions consistently is something i'd consider part of its SOTA capabilities.

Eventually i just tired of exploring. I just want stability.

Which ironically is why i'm thinking about moving from Claude. The very basic IDE/-p usage getting removed from my plan is a UX stability issue. I'm trying to progressively improve my workflows and efficiency, not have to establish a new foundation anytime something shifts. Quite frustrating.

Re: DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost

#120

Post by gck1 »

unshavedyak wrote: post #49

It'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 shortcut may not be used. It was a complete and utter failure.

GPT-5.5, on the other hand, blew me away. It just did the right things, didn't jump to next steps until it was sure it completed the initial layers and had a full understanding of what's required. The only time I prompted it during the 6 hours was when I saw it going in the right direction and I could nudge it slightly towards an even better way. I never felt I was fighting it. Okay, maybe a little bit - after compaction, it sometimes would go on a "no I'm not helping you with reverse engineering" tangent, but it would resolve in a clean session.

I cancelled my Claude subscription a month ago, so I haven't tested that, but DeepSeek has reminded me a lot of how I worked with Opus 4.6/4.7. Which perhaps could be a positive sign to some, but GPT-5.5 showed me that the way claude/ds work is just way too annoying.

Post reply on HN