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

261–270 of 325 posts

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

#261

Post by am17an »

Aurornis wrote: post #182
gck1 wrote: post #120

Earlier quoted context omitted.

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, b…

Did you read the OP when he's exactly chiding the model you're glazing?

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

#262

Post by schubidubiduba »

dominotw wrote: post #193
OtomotO wrote: post #179

Earlier quoted context omitted.

Exactly this. I don't care about the US more than about Russia or China these days. They are definitely not our allies anymore.

you dont need to be allies to do business. walmart is not my ally.

The difference is that Walmart is a stable, reliable trade partner that honors contracts and is not trying to use propaganda to make you a fascist

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

#263

Post by spacedcowboy »

bwfan123 wrote: post #5
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…

> 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.

I don't think DeepSeek v4 Flash is as good as Claude for relatively complex tasks. I ran with DeepSeek for a week, giving it the same sort of tasks that Claude normally does, and then ran Claude and asked it to continue. It found a whole bunch of things that had been "overlooked" by DeepSeek, and spent some time fixing them before wanting to move on.

DeepSeek is good, Claude is better, at least IMHO. Deepseek is a lot cheaper though :)

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

#264

Post by spacedcowboy »

Den_VR wrote: post #36
bwfan123 wrote: post #5

Earlier quoted context omitted.

> 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.

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

Somehow I don't think DeepSeek will be that interested in a 6502 compiler [1]...

1: https://atari-xt.com/

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

#265

Post by zaphirplane »

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…

Like which country allows companies to not follow a legal directive. How weird

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

#266

Post by qaz_plm »

raybb wrote: post #214
bwfan123 wrote: post #9

Earlier quoted context omitted.

In my experience, it is claude-code paired with deepseek-v4. For penny-pinchers like me, I can have long coding sessions with it with no anxiety about the cost. Also, prompting it to what you want and verifying the outputs is more important than the quality of the model. So, I am better off with a cheaper model and taking the responsibility for prompting it and verifying the results.

How to do connect deepseek to Claude code?

https://api-docs.deepseek.com/quick_start/agent_integrations...

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

#267

Post by Den_VR »

jack_pp wrote: post #132
Demiurge wrote: post #131

Earlier quoted context omitted.

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

I used to work with HVAC companies, and I noticed that many of their customers mistakenly believed they were purchasing air conditioners. They didn’t consider these devices, which they connected to the internet, as computers. Despite being systems that required user names, passwords, updates, monitoring, and other maintenance, the prevailing attitude among these customers was, “This is an appliance, and why would anyone care about my air conditioner?”

All this to say, not even subject matter experts necessarily appreciate the risk involved in their work

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

#268

Post by abustamam »

phrotoma wrote: post #257
jbellis wrote: post #156

As someone who has been writing harnesses for a year: the people at opencode etc aren't stupid, when they decide to break the prefix cache [usually partially] it's always because they've tested it and it gives better results overall. If you think that dsv4 behaves differently enough from the aggregate of other models, submit a PR with a patch to special case that to your harness of choice with evidence. Just blindly…

Is "harness" in this context ~= "agent"?

I've understood harness to be the software that runs the agent (open code, pi, Claude code)

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

#269

Post by ctxc »

mordae wrote: post #247
ctxc wrote: post #215

Earlier quoted context omitted.

Reads like a LOT of tokens to me. What does your usage /workflow look like? I'm v curious because although I do use Claude code, my token counts aren't nearly as much I want to know if I'm missing something cool!

Not OP, but I routinely load 150k tokens into context. A full sub-package to work on, select other files in the monorepo, e.g. front-end visualization and back-end data loader. Then work some 150k tokens, then start again. At the end, cache hit rate is like 99.5% if Novita is not having issues. For official DeepSeek API, 99.9% or something. Custom harness that never compacts or otherwise doctors the history.

Those numbers make sense to me...120 million input tokens is like 120 sessions of hitting the full context limit, which seems like a lot to me though

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

#270

Post by schaefer »

krm01 wrote: post #164
port11 wrote: post #155

Earlier quoted context omitted.

A lot of LLM-driven design now looks like this. I don’t understand how people don’t find ugly the pairings with an heavily italicised serif. You also can’t read much of the page on mobile, because the code example keeps shifting the content around. Now, that is overly critical, I’m sure their heart is in the right place. But a simpler website would do :)

It’s sad to see companies not spending a bit more on design. Sure, ai will help you get something decent out fast. But there’s a threshold where design becomes an indicator of trust. Especially for b2b software that tailor to large corps. Good design, character, adds directly to the bottom line.

> It’s sad to see companies…

The article is about an open source agent harness, Reasonix, that is built to leverage the DeepSeek native api.

There’s no company here. No design budget. These people are graciously sharing a project they made in their free time.

Post reply on HN