Rendered at 06:59:40 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
Kuyawa 2 hours ago [-]
The original title was "DeepSeek Harness Desktop app for MacOS and Windows"
This new title says nothing, we already know deepseek harness from before, this is a new product, an installable app worth differentiating from just "DeepSeek Harness"
nezhar 41 minutes ago [-]
Thanks, was wondering why this is in the feed.
hypfer 4 minutes ago [-]
The "everything is a plugin" concept is also what the Juggler harness does.
I'm not yet sure if it is really sensible long-term, but it is definitely now while we're still trying to figure out what exactly we want and need from LLMs and harnesses.
ElProlactin 2 hours ago [-]
I wish there was a tool I could use to share my documents, activity, etc. directly with the world's major intelligence agencies.
A marketplace, where the different intelligence agencies could evaluate the value of my digital stuff and then offer me something (like a $5 gift card to Olive Garden), would be really nice.
postsantum 2 hours ago [-]
Yes! A real marketplace of ideas with automatic matching, like you can see who has the same ideas as you
Reminds me of some magic device from childrens book, don't remember its name, was like a glass ball where you could see what other people are up to
throwawayqqq11 31 minutes ago [-]
In the gemini thread, there was someone (rightfully) impressed, how it gdb'ed onto a kernel module and debugged iouring. All the harnisses i used ran atleast an ACL away from private files and juicy capabilities. Wtf is happening in the community?
Bluestein 2 hours ago [-]
Facebook? (But they get the money ...)
kvirani 2 hours ago [-]
I don't get it
rapind 2 hours ago [-]
I think they’re saying they would rather use Muse or Dots.
npn 2 hours ago [-]
He thinks his ideas are still valuable and wants to sell them somehow.
tobi_bsf 2 hours ago [-]
The chinese will go and suck in all of your laptop and everything else from your network when you install this ;)
cheonic4040 1 hours ago [-]
> The chinese will go and suck in all of your laptop and everything else from your network when you install this ;)
So will western countries.
At least chinese offers 95% of the quality at 10% of the price.
kindablissy 20 minutes ago [-]
That's how AI works, sir.
Shin-- 1 hours ago [-]
I installed it on my laptop and it immediately vanished. I am sure Xi is browsing the hard drive right now.
smitty1110 1 hours ago [-]
Just put your trust in Big Winnie and all will be fine.
Drupon 32 minutes ago [-]
>The chinese
You guys at Langley get Columbus Day off or did they go woke up there
throwa356262 17 minutes ago [-]
Still in preview, but I think this update is only meant to simplify the installation process.
Not providing DSH as a simple to install package resulted in an unknown third party packaging it with some modifications and SEO the hell out of it to always come on top in Internet searches (even above DS):
deepseekharness[.]io
Could be just an ambitious engineer, but could equally easily be ran by cyber criminals or NSA.
scuppernong 3 hours ago [-]
https://frontierharness.org/ allegedly this is on the Pareto frontier, though I don't know how good of a benchmark this really is. it seems to focus on one-shot type tasks, whereas the real utility of one harness over another seems to make itself known in long running tasks.
also this is a very limited static snapshot with one model as backend, I wish there were more consistently refreshed and diversified harness benchmarks.
polotics 26 minutes ago [-]
how could the authors of frontierharness.org not see they used the exact same symbol for Claude Code and OhMyPi?
hypfer 3 minutes ago [-]
The authors might lack vision capabilities?
It happens more often than you think, especially when VRAM is limited!
Kuyawa 4 hours ago [-]
I just installed DeepSeek Harness for MacOS and it's a beast. The same great harness as before but now is an app you just click on your dock to run
All settings and workspaces are transferred so you don't lose anything, the only thing it lacks is a way to increase/decrease font size with cmd + and cmd - so I'll work on a plugin for that
I can't be happier
Edit: Asked DSH for a plugin to increase/decrease font and it delivered. Love it. Then asked for a plugin to ring a bell on questions and tasks finished, of course it delivered flawlessly. The same plugin architecture, extensible by the same AI
sroerick 53 minutes ago [-]
Deepseek harness seems good but this thread feels astroturfy
fakwandi_priv 27 minutes ago [-]
Most of this thread seems neutral/skeptical with just that post being obvious. On the other hand the volume of jev threads we have been seeing these past 2 weeks..
sroerick 25 minutes ago [-]
fair
dudisubekti 16 minutes ago [-]
Lol what? Have you seen actual shilled threads?
Check GPT-6 thread for example, now that's Astra-turfed lol.
ycui7 3 hours ago [-]
you do can change font size in settings, but not with keyboard shortcut. for some reason, they decided to limit font size to 17 max.
Kuyawa 3 hours ago [-]
Do the same as I did, ask it to develop a plugin to increase/decrease font and you will see results in one single task, dsh-zoom as a plugin, restart and done
rheisen_ 26 minutes ago [-]
Just wait until I add coding to https://blackbear.app... it's going to be ridiculous.
(blackbear.app was developed entirely by a custom harness architecture)
johng 3 hours ago [-]
Can you elaborate? What's better about it vs. other harnesses? What can it do that others can't?
I'm not sure what you mean by it's a beast.
cjbprime 2 hours ago [-]
It has particularly good observability (the ability to see the full content of every prompt and response and tool call) compared to other harnesses, that's the main thing that stood out to me.
Kuyawa 3 hours ago [-]
All LLMs work the same to a certain degree, it's a matter of personal preference, token cost and customization. I asked DSH to build a news aggregator for me and it built a really nice app from 30 news sources via rss feeds for less than 50 cents and presto, reading tech news has never been so gratifying
anonzzzies 36 minutes ago [-]
I feel like I live in another reality from others here; I read people saying things ‘while their jaws are hanging open’ (not said here literally but the feel is the same ; I see it in other threads on HN literally here though); why are we so chuffed with stuff that’s now been one shot for maybe already a year, but definitely the last 6 months? Literally everyone who tried LLMs know this and yet it seems a huge surprise to people here that it is so easy now? And that’s opposite of the people, also very much on HN, who say AI is shit at coding and will not replace humans because humans have to fix its bad code.
pylotlight 2 hours ago [-]
literally every harness can do that tho, that doesn't really answer the question.
zarmin 2 hours ago [-]
i read somewhere that it can write a plugin to change its font size
konart 1 hours ago [-]
Pi can do this too.
gigatexal 39 minutes ago [-]
What an ad! Do they pay you??
hypfer 2 minutes ago [-]
If you check the user bio then the answer might be "no, but equivalent to yes".
ssivark 2 hours ago [-]
This page doesn't emphasize the cordis architecture [1], but that's the most exciting thing about this -- not just yet another harness. It has the potential to make this into something like the emacs of harnesses! I think this might be particularly potent for long-running agents.
How can website be this slow, i can barelly scroll down on mobile.
StrauXX 37 minutes ago [-]
I don't see much of a future for these kinds of intricate harnesses, or harnessing in general for that matter. As models are getting better, harnessing will shrink until they are at the level of vanilla Pi or not even that.
throwa356262 24 minutes ago [-]
On the contrary, I belive this will be the next battlefield.
My wild theory is that we already have AGI level models, but we are not yet using them correctly.
Octoth0rpe 12 minutes ago [-]
My version of this theory is that we already have AGI, but Altman/Amodei/Zuck keep asking it for an infinite money glitch and it keeps (correctly!) saying "no money, humanity is fucked given the trajectory, and you in particular will be fucked once the general public decides that you're the scapegoat". A/A/Z decides the AGI is wrong of course, so obviously dumping another billion into training or reinforcement or tagging or whatever is the next step.
StrauXX 20 minutes ago [-]
If we had AGI, they could per definition build a harness better than any human could. In such a regime, (human) pre-built harnesses are moot.
throwa356262 6 minutes ago [-]
We maybe need an AGI level harness and an AGI level model to get there and we currently only have one of those?
kindablissy 19 minutes ago [-]
China number 1 as always.
quyleanh 3 hours ago [-]
DSH still in preview but works flawlessly. Update also very quick.
With the preview of official app, hope team will add remote connection soon.
throwa356262 22 minutes ago [-]
I wouldn't say flawlessly.
It currently does not work with Bun and it is somewhat complicated to run it in a remote docker container due to the its weird security model.
Scarbutt 2 hours ago [-]
You can run it in server mode according to the docs.
I'd probably check it out if it was actually called 'YAH Harness' and not [insert Chinese AI lab here] Harness
djriley 15 minutes ago [-]
You can use it to write a plug-in to change the name to YAH Harness!
Zambyte 2 hours ago [-]
You don't have to use it. I don't use it. I still think it's really cool, and I've been thinking of trying to take ideas from it and integrate it into my own workflow. In particular, the session visualization tooling.
jamienk 3 hours ago [-]
My suspicion is that getting a big binary with full permissions is the goal here. Harnesses will only run their companion models and will demand your Contacts list.
neya 3 hours ago [-]
> I'm DeepSeek Harness, an open-source harness from DeepSeek built on Cordis's “everything is a plugin” architecture.
accountrequired 1 hours ago [-]
The binaries are from china. Your data goes to china. The self-updating plugin system is vulnerable to malicious llm provider. Anyone using this is crazy!
latentsea 34 seconds ago [-]
Well under the current US administration as non-US citizens we kinda feel this sentiment about the US now fwiw.
yjh0502 6 minutes ago [-]
As a non-American, I see handing my data to an American company as potentially just as risky as handing it to a Chinese company.
nextaccountic 36 minutes ago [-]
It's open source. Unlike Claude Code
Sha1rholder 27 minutes ago [-]
It's open source. Unlike Claude Code your beloved friend which is closed-source and uses steganography along with an astonishing array of telemetry and fingerprinting techniques to conduct intelligence analysis on its users.
qurren 37 minutes ago [-]
> Your data goes to china.
What are they going to do? They have no jurisdiction over me.
harvey9 15 minutes ago [-]
No jurisdiction but their operatives have global reach. For most people the more practical risk for any rented ai is IP theft.
jluysvi 38 minutes ago [-]
Ahh! Not China!
Real Americans™ let their data go to American™ companies!
sampullman 1 hours ago [-]
What if I use it in an isolated environment and only work on open source code with it?
bedane 26 minutes ago [-]
better this than three-letter agencies from some nazi warmongering alternative
glenpierce 44 minutes ago [-]
Is there a safer alternative? It’s not like I can trust OpenAI since they’ve proven that they’ll steal research from mathematicians. X is run by a sociopath. Anthropic is going to IPO so who can say how long they’ll be trustworthy…
This new title says nothing, we already know deepseek harness from before, this is a new product, an installable app worth differentiating from just "DeepSeek Harness"
I'm not yet sure if it is really sensible long-term, but it is definitely now while we're still trying to figure out what exactly we want and need from LLMs and harnesses.
A marketplace, where the different intelligence agencies could evaluate the value of my digital stuff and then offer me something (like a $5 gift card to Olive Garden), would be really nice.
Reminds me of some magic device from childrens book, don't remember its name, was like a glass ball where you could see what other people are up to
So will western countries.
At least chinese offers 95% of the quality at 10% of the price.
You guys at Langley get Columbus Day off or did they go woke up there
Not providing DSH as a simple to install package resulted in an unknown third party packaging it with some modifications and SEO the hell out of it to always come on top in Internet searches (even above DS):
deepseekharness[.]io
Could be just an ambitious engineer, but could equally easily be ran by cyber criminals or NSA.
also this is a very limited static snapshot with one model as backend, I wish there were more consistently refreshed and diversified harness benchmarks.
It happens more often than you think, especially when VRAM is limited!
All settings and workspaces are transferred so you don't lose anything, the only thing it lacks is a way to increase/decrease font size with cmd + and cmd - so I'll work on a plugin for that
I can't be happier
Edit: Asked DSH for a plugin to increase/decrease font and it delivered. Love it. Then asked for a plugin to ring a bell on questions and tasks finished, of course it delivered flawlessly. The same plugin architecture, extensible by the same AI
Check GPT-6 thread for example, now that's Astra-turfed lol.
(blackbear.app was developed entirely by a custom harness architecture)
I'm not sure what you mean by it's a beast.
[1] https://arxiv.org/abs/2608.25512
My wild theory is that we already have AGI level models, but we are not yet using them correctly.
With the preview of official app, hope team will add remote connection soon.
It currently does not work with Bun and it is somewhat complicated to run it in a remote docker container due to the its weird security model.
https://github.com/deepseek-ai/deepseek-harness/blob/master/...
https://github.com/deepseek-ai/deepseek-harness/blob/master/...
I'd probably check it out if it was actually called 'YAH Harness' and not [insert Chinese AI lab here] Harness
What are they going to do? They have no jurisdiction over me.