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

131–140 of 325 posts

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

#131

Post by Demiurge »

jack_pp wrote: post #94
embedding-shape wrote: post #46

Earlier quoted context omitted.

Not everyone is working with state secrets or user personal data (or even more closely guarded, company secrets) on a daily basis, most of what I hack on is either FOSS already, or will be, not much to keep secret here. Obviously, if you do deal with any sort of secrets, then using local LLMs over OpenAI, Anthropic, DeepSeek or whoever is obviously preferred, and in the case of personal data of users, probably a requ…

either this or you work on software that even if copied won't get you far since the business relies on network effects or pure networking. Getting the source code of facebook or instagram doesn't mean you could compete with them. I work for a company that has built relationship with event organizers over the past 10 years. The code I maintain could be written from scratch in maybe 2-3 months even though it was built…

I actually agree with you, for the most part. The code I work with actually does contain some valuable algorithms, but Im pretty sure the effort of integrating them into a larger system is pointless without the data. It’s almost like stealing half-life 2 source code without any assets.

Still, “Getting the source code of facebook or instagram doesn't mean you could compete with them.” I think to giants like that, having access to their source code could open up some very interesting loop holes for manipulating the ranking algorithms, or even security vulnerabilities.

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

#132

Post by jack_pp »

Demiurge wrote: post #131
jack_pp wrote: post #94

Earlier quoted context omitted.

either this or you work on software that even if copied won't get you far since the business relies on network effects or pure networking. Getting the source code of facebook or instagram doesn't mean you could compete with them. I work for a company that has built relationship with event organizers over the past 10 years. The code I maintain could be written from scratch in maybe 2-3 months even though it was built…

I actually agree with you, for the most part. The code I work with actually does contain some valuable algorithms, but Im pretty sure the effort of integrating them into a larger system is pointless without the data. It’s almost like stealing half-life 2 source code without any assets. Still, “Getting the source code of facebook or instagram doesn't mean you could compete with them.” I think to giants like that, havi…

True, haven't thought of that. However very few actual projects / companies are in a situation where the chinese GOVT would be interested to spend resources to hack your platform. For the ones that are afraid of that there's always self hosting of course

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

#133

Post by carterschonwald »

i cant find anything substantiated in the code that actually differentiates it from any other harness.

my fork of oh my pi that i have a lot of experiments in, is lterally designed to only work well with models that have decent reasoning levels, like deep seek models. check it out!

https://github.com/cartazio/oh-punkin-pi/blob/main/scripts/b... — thats the install script for after clone

fair warning: tis my dog food test bed as i build even fancier stuff

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

#134

Post by eikenberry »

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!

Maybe check out Goose. It is the standard agent harness being developed by The Linux Foundation under the AAIF. Under active development and the implementation seems to have a good leg up on the other popular agents.

https://github.com/aaif-goose/goose

https://goose-docs.ai/

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

#135

Post by gck1 »

chuckadams wrote: post #115
droidjj wrote: post #110

Earlier quoted context omitted.

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.

I think pi wants you to write your own extensions, adapted to your meeds.

I haven't had a need for any extensions though. Maybe subagents, but I solved that with tmux. For all the rest, I just use "skills".

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

#136

Post by tim-projects »

jijji wrote: post #83
Den_VR wrote: post #36

Earlier quoted context omitted.

I’m feeling more a novice every day, but how isn’t this just handing over your code to team deepseek for whatever they might want

there's laws on the books in China that says that every company operating in China must aid and abet the Chinese government in espionage against the rest of the world. given those facts, I find it deeply troubling to be using anything coming out of China, especially a program that runs in the context of a Linux terminal on a machine that might have something important on it. I'd argue it's a back door waiting to happ…

Is it not better to have a country far away spying on you than your own country?

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

#137

Post by hirako2000 »

dathery wrote: post #87
3uler wrote: post #31

Earlier quoted context omitted.

Opencode has really bad cache stability issues that they seem uninterested in fixing at the moment.

The OpenCode devs talk about this on Twitter a lot, e.g. https://xcancel.com/thdxr/status/2048268697790300343 > tool call pruning breaks cache and people will tell you this is horrible and expensive > except i looked at some anthropic data and real user behavior ends up with better cache hits and 30% less spend > even this is needs to be analyzed further, it's just not simple > for openai data it's inverted! cache hi…

They are. Empirical evidence on my side. Because attention is sparse across the context. It's not truly treating a million token the way it treats a fraction of that count. For performance.

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

#139

Post by snqb »

wg0 wrote: post #121

Performance is horrible when you type but caching is magical. Extremely pro consumer tool. I have been hammering it hard with 97% cache utilization and barely $0.03 dollar spent for me constantly exploring a codebase.

Deepseek API caches very efficiently itself. I use it heavily via pi agent, and a lot of times I get 99%+ caching for longer sessions.

Have you tried using Deepseek API via other agents? This project tbh looks like a S-tier slop

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

#140

Post by abalashov »

throw10920 wrote: post #63
abalashov wrote: post #61

Earlier quoted context omitted.

Although I have little interest in agentic coding, when I do use it, I have found Kimi K2.6 to give Opus-quality output, and have switched entirely to it for pretty much everything.

I've used Opus extensively and tried K2.6 on a few projects, and the gap is huge . K2.6 is nowhere near the performance of Opus. That's fine because it's also far cheaper, but public benchmarks line up with my own personal experience that they aren't comparable in terms of intelligence. (that is, different places on the Pareto efficiency graph)

No two uses are alike, I suppose. For me, whatever difference is a wash. However, I probably tend to shy away from throwing high-complexity/long-horizon tasks at the model.
Post reply on HN