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
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
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.
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.
Weird. I don't use the official harnesses by OpenAI or Anthropic but with all others i tried there wasn't a single one that hides any of that. What harnesses did you compare to?
I think what he meant was that it gives you good overall observabiity, over your entire context, kind of how langfuse or these platforms do, but it does so locally. A good philosophy i picked up is how they treat the transcript as the backbone of the product.
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..
It works with lots of providers, including local ones.
After you log in, click on your name/picture in the bottom left, Settings, Models. Has a huge list of models supported in the dropdown, plus a "custom model API" tab where you put in the name you want, the base URL, the protocol, and your API key.
Did I miss something? A lot of people in this thread are saying that DeepSeek Harness is closed source but a quick search leads me to this:
>DeepSeek Harness (dsh) is an open-source agent harness developed by DeepSeek AI.
>It is built on an everything-is-a-plugin architecture and powered by Cordis, whose design is described in A Programming Paradigm for Spatiotemporal Composability.
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.
i've seen "Pareto frontier" literally 500 thousand times in the last two weeks or so, and maybe once or twice before that. Can someone please explain what happened recently
i think you still don't understand what it means. there's nothing personal about it. the point you pick along the frontier is what's personal to you and your needs. the frontier itself is not.
The fancy expensive chocolate bar that's incredible quality and the cheap reasonable quality one can both be good value. You can draw a beautiful line and pick any along that line.
You could call that the Pareto frontier of chocolate, or you could call it cost/benefit analysis or you could just say this is where you're currently getting the best value.
I would guess that the article came out because the term was getting popular in AI/LLM circles for measuring LLM cost-for-performance metrics. It was probably riding the meme up the wave, rather than fundamentally triggering it.
So for me, literally I was trying to solve a problem with an AI agent and it threw the term at me. It is a real and useful concept, but my hypothesis is that a certain AI release started using and a bunch of people said "Oh this makes me sound smart/trendy" and started using it every chance they got.
We like to think we aren't token predictors, but the amount of sheer regurgitation I see from us humans makes me wonder (also "commoditize your complement", and so many others)
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.
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.
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.
Being Danish I'd probably rate it China > you > US. Realistically though, I'm probably sending everything to everyone except for you.
I rate the US last because the US government shares information with European governments, so it's the most likely to affect me. I wrote this next to my dishwasher though, and if it's anything like those LG tv's it probably identified what I wrote from the keystroke sounds or something.
I live in China, they already have everything, especially when using appl products. It is basically mandatory here since privacy is a completely different concept here (not sure its even a concept here tbh. Although there are some privacy laws)
Why the fuck would I care? The spooks definitely won't. I'm one person on a planet of 8 billion.
I think people don't appreciate the scale of that. A person is like a pixel on a 4k screen, in a wall that's made of many screens (about 5 in case of my country, about 42 in case of the US). Nobody cares what the single pixel does. It's not even visible unless it's so broken it doesn't change the same way surrounding pixels do.
I have a feeling that all this privacy obsession is actually a reaction to the unconscious feeling of irrelevance at this scale. In their minds, people defy the fact they're just sand for the systems of modern civilization - no, they are the very special ones, each fancies themselves a player among billions of NPCs, and to prove their uniqueness and specialness, they want to hide that fact from other NPCs, and get annoyed at the notion the world may indeed discover they are special.
Nothing else makes sense. Not in the west at least, where the only realistic threat from loss of privacy is getting weirder ads (hint: a real power move is to start with ad blocking and removing ads - and ad-infested media sources - from your life).
Now, loss of control over your daily life and your computing devices, that's another story. But most people don't seem to care about those.
You're talking about privacy from governments, which I agree os an overblown concern unless you're some sort of political activist/dissident.
However, privacy from mega corpos is an entirely different matter, because they CARE about you(r data) and rather than a pixel, you're a fully fleshed out record in their gigantic databases and they use this data to profit off of you, in multiple ways that all can be described as "scamming you out of money" by way 0f perfecting the art of selling you shit you don't need.
And then you have the wannabes, mid-sized corpos with security postures so poor every hacker and their grandmother has your data, for the sole purpose of scamming your own grandmother.
Deep inside they're realizing that the whole privacy thing is overblown obsession, and nobody actually cares about their data, and they wish someone did, but clearly no one does, not even $5 gift card for everything there is to know about one.
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?
Not that long ago, the joke was about grandparents installing every available toolbar into IE and getting hacked because "oh, neat! I want that!" without thinking about it.
Yeah, I know that one, but I actually looked into one and found nothing interesting. Mostly a bunch of paranoid people obsessed with "intelligence agencies" constantly looking through their sock drawers, as if spooks had literally nothing better to do with their time.
Teacher of mine spent almost 20 years getting access to his FBI file through FOIA requests. Apparently it was surprising how much of his life they didn't know about.
Children with no life have never had anything worth keeping private. Even the question of having nothing to hide is foreign if you've never done anything at all.
It's like that parable about God giving us free will. If or when the intelligence agencies manage to create a generation with nothing to hide, what will their purpose be? You might as well take field notes on birds or sheep.
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 and worth differentiating from just "DeepSeek Harness"
It's no that fancy when is put in practical engineering terms. I've spend some time with the paper.
Paper describes such system whch has ability to enable/disable capabilities without process restart. Each plugin must follow specific shape: function to activate, function to deactivate it (both working, mutating the same shared context object), describe provided and required services. This, plus some ideas, like "every provider must outlive consumers when destructred" allows plug-n-play ensuring all dependencies are satisfied before the plugin is activated, lazy activation, and plugin deactivation/destruction.
What makes this great is infinite hack-ability of the interface and agents have become pretty good at writing elisp packages, so basically you can have a workflow exactly how you want.
I wish I had time to make a screencast about this, but If you are a Emacs user and not using Emacs for agentic stuff, you are missing out IMO.
In my time using it with GLM 5.2, I've observed it modify itself to disassemble binaries in search of answers - without me needing to ask it to do so. Very powerful stuff. Here's what it looked like:
◇ reasoning summary
│ The 200MB binary grep with regex backtracking is too slow. Let me write the strings out first (using grep -a with simple fixed patterns is fine; regex with .{0,80} on binary is slow). Better: use SBCL to do
│ a fast binary search, or use tr to split null-separated strings then grep fixed strings. Let me use a quick approach: grep -ao with fixed patterns only (no regex), which was fast before.
│
│ To extract context, I can use SBCL to load the file into memory (206MB is fine) and search for occurrences with bounded context. Let me do it in a Lisp worker.
▸ lisp.eval
(lisp.eval :form "(with-open-file (in \"/nix/store/g7b3p8ypxmdycry9wilil8mwl084kplw-antigravity-cli-1.1.19/bin/agy\" :element-type '(unsigned-byte 8))
(let* ((data (make-array (file-length in) :element-type '(unsigned-byte 8)))
(_ (read-sequence data in))
(haystack (sb-ext:octets-to-string data :external-format :latin-1)))
(flet ((find-all (needle)
(let ((out '()) (start 0))
(loop for pos = (search needle haystack :start2 start)
while pos do (push pos out) (setf start (+ pos (length needle))))
… +10 more lines
│ (with-open-file (in "/nix/store/g7b3p8ypxmdycry9wilil8mwl084kplw-antigravity-cli-1.1.19/bin/agy" :element-type '(unsigned-byte 8))
│ (let* ((data (make-array (file-length in) :element-type '(unsigned-byte 8)))
│ (_ (read-sequence data in))
│ (haystack (sb-ext:octets-to-string data :external-format :latin-1)))
│ (flet ((find-all (needle)
│ (let ((out '()) (start 0))
│ (loop for pos = (search needle haystack :start2 start)
│ while pos do (push pos out) (setf start (+ pos (length needle))))
│ … +9 more lines
lisp.eval cpu 0.205s · real 4.018s
│ Output:
│ settings.json positions: (89311959 90892289 90918553 90945997 90985371 91164238
│ 91164426 91171707 91275241 91297838 91299802 91299923
│ 91629274 96365298 96370345 96398990 96405347 96406738
│ 96414968 96419796 96426018 96429189)
│ --- 89311959
│ oughDependency: NestedType: OutputType: Deprecated: AllowAlias: Annotation: SourceFile: rsa-sha2-512rsa-sha2-256hmac-sha1-96ssh-userauthkey exchangedirect-tcpipForwardAgentGatewayPortsTCPKeepAlivedefault no…
│ --- 90892289
│ ks=%v)conversation file not found in source directory: %sfailed to create cache directory for conv cache: %vBalanced speed and reasoning quality for most tasksPrepared switch to default agent (will %s on ex…
│ --- 90918553
│ on-interface type passed to Type.Implementsreflect.Value.Slice: string slice index out of boundsUse /feedback to share your experience with the team.Transition failed: ForkConversation returned empty IDpers…
│ --- 90945997
… +14 more lines
◇ reasoning summary
│ The binary confirms:
│ - modelProvider in settings.json selects the Gemini API backend with GEMINI_API_KEY.
│ - There's a regex ^(?:gemini-api:|blade:|evergreen:|beyond-api:)(?:.*?/models/(.+)|(?:.*/)?([^/]+))$ — model references with provider prefixes.
│ - "No title command configured in settings.json. ...
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!
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…
Both Z.AI and xAI have already proven you can't trust them, like at all. I guess other harnesses are in "I don't trust it, but it is convenient" category.
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.
The new danger is US administration and the current fascit regime. China has yet not topple a single government abroad, has not bombed a single country and has not tapped the phones of its allies.
Now don't down vote before understanding the definition of a fasict:
"A fascist is a person who advocates for or adheres to fascism, a far-right, authoritarian, and ultranationalist political ideology."
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.
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.
Exactly, sometimes when reading Hacker News I get the impression this thing is a cult. Luckily there's still some dissident voice around to keep it interesting
drives me up the wall, this shifting definition of AGI; folks, when we no longer need to train AI models at all because we have finally developed artificial comprehension is AGI. This propaganda imposed definition is for fools and sycophants.
> As models are getting better, harnessing will shrink
That can be true only for locally hosted models. The more supplied tools can do, the less data has to be exchanged with OpenAI/Anthropic servers. So bad harness means both higher lag and token usage.
Nah. Model efficiency is determined by the harness. The model needs a ton of support to connect to its surrounding services. Sure, it can built a lot of that itself, but the infrastructure needs to exist.
Still in preview, but I think this is their response to DSH being har to get working before which resulted in an unknown third party packaging it with some modifications and SEO the hell out of it to always come on top of Internet search (even above DS):
deepseekharness[.]io
Could be just an ambitious engineer, but could equally easily be ran by cyber criminals or NSA.
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.
FWIW, making juggler plugin based feels quite normal to me, coming from the world of audio software, where that entire industry is still based around many thousands of VST/AudioUnit plugins which run native un-sandboxed code in the host apps, with access to absolutely anything they want. And it's somehow all just kind of been OK..
DeepSeek harness is the OpenCode (better than OpenCode) of the web/desktop medium.
Good things about it are that it is extremely lightweight and fast. The communication between sub agents is two way in that a sub agent can midway send a message to parent and the parent can send a message midway to change the course of action of a sub agent and while this is happening, you can sitll continue talking to the model on the main thread.
Downside of DeepSeek is that it is constantly in flux which is understandable and they make it very clear themselves that the breaking changes are to be expected.
I’m kind of into OpenCode, in the sense that it’s the best version of what I want (complete, well engineered and configurable/extensible harness server with an efficient remotely connectable UI). I have a good share of issues with it, a lot of it being inexplicable behavior (slowdowns, bugs/glitches, state not being observable).
This description gives me hope that DSH might fit the bill even better - let’s hope their UI API is stable and remotely usable.
Anyone know if this works with local models or only the APIs for DeepSeek? I'm assuming it's with the API, but I'm looking for cutting edge local harnesses.
To be fair, when it is good people copy anyway. All companies do benchmarks and analysis of competitors. The criticism of china was that you sent them a thing go produce and your design would appear somewhere else which could essentially bankrupt you business.
That said, I have the impression this still exists but is less and less relevant for them to keep doing it.
China is the one saying nations should gather and stop doing poo-poo decisions to economy while another one keeps saying that everyone else but them is evil.
I honestly think this scarcity and shortages are all artificial and caused by the same group of people. They don't even fake anymore
True.
if I remember correctly, there was a Louis Vuitton process against a Chinese marker saying they were provided with official build of materials and plans for production. What the copycat factory did was to make the process cheaper but use almost the same of materials and design.
It seems the same copycat later then start hiring the same Italian studios to design their own products.
This does not relate to what I posted, but if you want to know: The trouble with China from the perspective of American foreign policy is not about copying intellectual property (Japan did that through the 1970s until Reagan put sanctions on them).
Since Nixon opened the door to China, American policy has been based on the idea that a strong Chinese economy which lifted a billion people out of poverty would lead, inexorably, to Chinese Democracy. This would make China not only a trading partner, but an ally with an interest in protecting human rights and democratic ideals.
You can laugh at this notion, but this is really what Nixon, Reagan, Bush and Clinton believed would happen...
Around the time the Chinese government shot its protesters in Tiananmen Square, it started to become obvious to some that the CCP was capable of enriching itself and improving the economic circumstances of its subjects in a way that would still prevent any sort of free speech or free action for its population. In fact, it even increased the enslavement of its denizens using the money and technology we had provided.
Our intention was to make China a middle class nation, because we believed that a middle class nation would ultimately rebel against a dictatorship and demand the same kind of human rights and liberties that we demand, or Europe demands, as nations of economically free individuals, families and competing corporations. But that did not happen. Instead, we seem to have accidentally fed the dictatorship.
That is the true state of affairs in US/China relations. Both sides know it. We would prefer Chinese democracy. The CCP's only interest is in maintaining its own absolute power.
Whatever reference you're making to "the same group of people" is foolish and ridiculous if you understand even a tiny bit of the history of what was attempted in the economic opening of US markets to China.
And it is clear now that, given the opportunity to become a free nation, it was China which failed to give its citizens rights, and which failed to launch a free political debate about its own future. This has led to internal stagnation and absurd expenses on militarization with no benefit for the people. It is socialist in name only, the only "socialist" country in history which doesn't even attempt to provide any services for its people, nor any democratic path to change its governmental structure.
In the long run, communist China is just another dynasty nearing the end of its mandate from heaven. But there are those of us who think that China could be a country whose wealth and power would triple overnight if the economic prosperity were coupled with political and indidual freedom as we have in the West.
That all being said, I understand you were just trying to inject some lousy conspiracy minded antisemitism here, and you're not really anyone worth talking to; I'm just writing this for whoever else comes along and sees it.
> You can laugh at this notion, but this is really what Nixon, Reagan, Bush and Clinton believed would happen...
Why would anyone laugh when at some point political parties were literally killing people and feeding human meat to others there
An unstable power in Asia could mean ruin for a whole economic system. It was only logic that stabilizing the system would, at least make the problem slow down for another decade.
I am not sure what Nixon really thought about it, but I think it is fair to say that's what happened.
I don't really get what possibly on what I said to be ASmt?
Edit: oh I see! You thought I said "the same evil people" and it. No! Totally completely not it. Lol. I did not even considered that it could be read like this. I don't believe that a religion of any sort by itself would do this.
Have you read The World Restored? The first part is boring AF, but we are living through a spiral of the send part of that book.
That wasn't my critique. What I wrote had nothing to do with China, or copying. Also nothing to do with govt backdoors in bios chips or routers.
I don't want to install some software that exfiltrates all my passwords. Just because some hardware backdoors may already exist, how on earth does that mean I should stop caring what software I give root access to?
A basic rule of security is that no system is 100% secure, not even if it's air gapped and 1km underground. Your job is not to say "well fuckit, let's download this shady software because nothing is safe anyway." It's to prevent opening any holes you can prevent opening, and do your diligence on anything you can mitigate, because stopping 99% of threats is better than stopping 98%. Or in this case, much better than straight up allowing unknown people to root your server.
If you're using Mistral Vibe installed on your computer, that is a harness. Vibe is one of many AI harnesses.
In general, a harness is something that lets your AI use tools on your computer and lets it work independently while you walk away. (Very simplified definition, not all harnesses are that automated.)
It's a long time since I tried Vibe, but when I did it was one of the worst. Back then it had broken support for MCP or computer use and other tools people now regard as near essential in AI. Hopefully Vibe is better now. Sadly Mistral are a long way behind.
Mistral Vibe lets you use GLM-5.3 by default now. So it's a very capable model, for a cheap monthly fee. The Web version is excellent : tried yesterday on a simple search, results were way more informative than ChatGPT.
But yes, it's sad that they don't release models anymore.
I've been with Mistral for a while now. Their hosted GLM-5.3 has been a game changer in Vibe CLI over the last couple of weeks. The Vibe CLI harness has been improving for a while, but is still a little sluggish and I feel lacks token minimisation strategies. I recently changed to Maki and have been reasonably satisfied so far.
However, I also use the Mistral Vibe chat in my browser. I think they only switched to GLM-3.5 here a couple of days ago (https://docs.mistral.ai/resources/changelogs). It'd be nice if Mistral had a desktop client, but I have Goose installed which I have no real complaints about.
Captcha had me ruffled at the onset as I am slightly visually impaired and couldn't pick out the somewhat grainy images. It seems to be the standard now.
212 comments
[ 2.0 ms ] story [ 40.7 ms ] threadAll 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
I'm not sure what you mean by it's a beast.
Check GPT-6 thread for example, now that's Astra-turfed lol.
(blackbear.app was developed entirely by a custom harness architecture)
After you log in, click on your name/picture in the bottom left, Settings, Models. Has a huge list of models supported in the dropdown, plus a "custom model API" tab where you put in the name you want, the base URL, the protocol, and your API key.
Now, if only DeepSeek Harness were open source…
>DeepSeek Harness (dsh) is an open-source agent harness developed by DeepSeek AI.
>It is built on an everything-is-a-plugin architecture and powered by Cordis, whose design is described in A Programming Paradigm for Spatiotemporal Composability.
https://github.com/deepseek-ai/deepseek-harness
Now, this could simply be an attempt at sarcasm but it's getting really hard to tell.
It happens more often than you think, especially when VRAM is limited!
You could call that the Pareto frontier of chocolate, or you could call it cost/benefit analysis or you could just say this is where you're currently getting the best value.
[0]: https://trends.google.com/trends/explore?date=all&q=pareto%2...
[1]: https://books.google.com/ngrams/graph?content=pareto+frontie...
We like to think we aren't token predictors, but the amount of sheer regurgitation I see from us humans makes me wonder (also "commoditize your complement", and so many others)
I'd probably check it out if it was actually called 'YAH Harness' and not [insert Chinese AI lab here] Harness
With the preview of official app, hope team will add remote connection soon.
https://github.com/deepseek-ai/deepseek-harness/blob/master/...
https://github.com/deepseek-ai/deepseek-harness/blob/master/...
It currently does not work with Bun and it is somewhat complicated to run this in a remote docker container due to the weird security model it uses.
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.
I rate the US last because the US government shares information with European governments, so it's the most likely to affect me. I wrote this next to my dishwasher though, and if it's anything like those LG tv's it probably identified what I wrote from the keystroke sounds or something.
Why the fuck would I care? The spooks definitely won't. I'm one person on a planet of 8 billion.
I think people don't appreciate the scale of that. A person is like a pixel on a 4k screen, in a wall that's made of many screens (about 5 in case of my country, about 42 in case of the US). Nobody cares what the single pixel does. It's not even visible unless it's so broken it doesn't change the same way surrounding pixels do.
I have a feeling that all this privacy obsession is actually a reaction to the unconscious feeling of irrelevance at this scale. In their minds, people defy the fact they're just sand for the systems of modern civilization - no, they are the very special ones, each fancies themselves a player among billions of NPCs, and to prove their uniqueness and specialness, they want to hide that fact from other NPCs, and get annoyed at the notion the world may indeed discover they are special.
Nothing else makes sense. Not in the west at least, where the only realistic threat from loss of privacy is getting weirder ads (hint: a real power move is to start with ad blocking and removing ads - and ad-infested media sources - from your life).
Now, loss of control over your daily life and your computing devices, that's another story. But most people don't seem to care about those.
However, privacy from mega corpos is an entirely different matter, because they CARE about you(r data) and rather than a pixel, you're a fully fleshed out record in their gigantic databases and they use this data to profit off of you, in multiple ways that all can be described as "scamming you out of money" by way 0f perfecting the art of selling you shit you don't need.
And then you have the wannabes, mid-sized corpos with security postures so poor every hacker and their grandmother has your data, for the sole purpose of scamming your own grandmother.
Is that really too much to ask for?
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
oh, good old times of PRISM, rightly bygone. Of course they don't do this now.
Children with no life have never had anything worth keeping private. Even the question of having nothing to hide is foreign if you've never done anything at all.
It's like that parable about God giving us free will. If or when the intelligence agencies manage to create a generation with nothing to hide, what will their purpose be? You might as well take field notes on birds or sheep.
This new title says nothing, we already know deepseek harness from before, this is a new product, an installable app and worth differentiating from just "DeepSeek Harness"
Paper describes such system whch has ability to enable/disable capabilities without process restart. Each plugin must follow specific shape: function to activate, function to deactivate it (both working, mutating the same shared context object), describe provided and required services. This, plus some ideas, like "every provider must outlive consumers when destructred" allows plug-n-play ensuring all dependencies are satisfied before the plugin is activated, lazy activation, and plugin deactivation/destruction.
What makes this great is infinite hack-ability of the interface and agents have become pretty good at writing elisp packages, so basically you can have a workflow exactly how you want.
I wish I had time to make a screencast about this, but If you are a Emacs user and not using Emacs for agentic stuff, you are missing out IMO.
Would you be interested in a self-modifying harness written in Common Lisp? If so, then please check out Autolith: https://github.com/lambda-symbolics/autolith/
In my time using it with GLM 5.2, I've observed it modify itself to disassemble binaries in search of answers - without me needing to ask it to do so. Very powerful stuff. Here's what it looked like:
(The name sounds a bit like autolytic, evoking self-harm. Which may be appropriate after all.)
And Pi is considered the neutral choice: https://news.ycombinator.com/item?id=49926069
What are they going to do? They have no jurisdiction over me.
Now don't down vote before understanding the definition of a fasict:
"A fascist is a person who advocates for or adheres to fascism, a far-right, authoritarian, and ultranationalist political ideology."
China is none of that.
My wild theory is that we already have AGI level models, but we are not yet using them correctly.
Kind of like how we all fail to see the bearded guy in the sky.
I think that harnesses for LLMs are as important as IDEs for languages.
That can be true only for locally hosted models. The more supplied tools can do, the less data has to be exchanged with OpenAI/Anthropic servers. So bad harness means both higher lag and token usage.
deepseekharness[.]io
Could be just an ambitious engineer, but could equally easily be ran by cyber criminals or NSA.
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.
Good things about it are that it is extremely lightweight and fast. The communication between sub agents is two way in that a sub agent can midway send a message to parent and the parent can send a message midway to change the course of action of a sub agent and while this is happening, you can sitll continue talking to the model on the main thread.
Downside of DeepSeek is that it is constantly in flux which is understandable and they make it very clear themselves that the breaking changes are to be expected.
This description gives me hope that DSH might fit the bill even better - let’s hope their UI API is stable and remotely usable.
Meanwhile there is an american backdoor in your bios, cpu and router
That said, I have the impression this still exists but is less and less relevant for them to keep doing it.
China is the one saying nations should gather and stop doing poo-poo decisions to economy while another one keeps saying that everyone else but them is evil.
I honestly think this scarcity and shortages are all artificial and caused by the same group of people. They don't even fake anymore
I don't know...
Now you don't need to send them the design, a LLM can reproduce it from photos :)
It seems the same copycat later then start hiring the same Italian studios to design their own products.
Since Nixon opened the door to China, American policy has been based on the idea that a strong Chinese economy which lifted a billion people out of poverty would lead, inexorably, to Chinese Democracy. This would make China not only a trading partner, but an ally with an interest in protecting human rights and democratic ideals.
You can laugh at this notion, but this is really what Nixon, Reagan, Bush and Clinton believed would happen...
Around the time the Chinese government shot its protesters in Tiananmen Square, it started to become obvious to some that the CCP was capable of enriching itself and improving the economic circumstances of its subjects in a way that would still prevent any sort of free speech or free action for its population. In fact, it even increased the enslavement of its denizens using the money and technology we had provided.
Our intention was to make China a middle class nation, because we believed that a middle class nation would ultimately rebel against a dictatorship and demand the same kind of human rights and liberties that we demand, or Europe demands, as nations of economically free individuals, families and competing corporations. But that did not happen. Instead, we seem to have accidentally fed the dictatorship.
That is the true state of affairs in US/China relations. Both sides know it. We would prefer Chinese democracy. The CCP's only interest is in maintaining its own absolute power.
Whatever reference you're making to "the same group of people" is foolish and ridiculous if you understand even a tiny bit of the history of what was attempted in the economic opening of US markets to China.
And it is clear now that, given the opportunity to become a free nation, it was China which failed to give its citizens rights, and which failed to launch a free political debate about its own future. This has led to internal stagnation and absurd expenses on militarization with no benefit for the people. It is socialist in name only, the only "socialist" country in history which doesn't even attempt to provide any services for its people, nor any democratic path to change its governmental structure.
In the long run, communist China is just another dynasty nearing the end of its mandate from heaven. But there are those of us who think that China could be a country whose wealth and power would triple overnight if the economic prosperity were coupled with political and indidual freedom as we have in the West.
That all being said, I understand you were just trying to inject some lousy conspiracy minded antisemitism here, and you're not really anyone worth talking to; I'm just writing this for whoever else comes along and sees it.
Why would anyone laugh when at some point political parties were literally killing people and feeding human meat to others there An unstable power in Asia could mean ruin for a whole economic system. It was only logic that stabilizing the system would, at least make the problem slow down for another decade.
I am not sure what Nixon really thought about it, but I think it is fair to say that's what happened.
I don't really get what possibly on what I said to be ASmt?
Edit: oh I see! You thought I said "the same evil people" and it. No! Totally completely not it. Lol. I did not even considered that it could be read like this. I don't believe that a religion of any sort by itself would do this.
Have you read The World Restored? The first part is boring AF, but we are living through a spiral of the send part of that book.
I don't want to install some software that exfiltrates all my passwords. Just because some hardware backdoors may already exist, how on earth does that mean I should stop caring what software I give root access to?
A basic rule of security is that no system is 100% secure, not even if it's air gapped and 1km underground. Your job is not to say "well fuckit, let's download this shady software because nothing is safe anyway." It's to prevent opening any holes you can prevent opening, and do your diligence on anything you can mitigate, because stopping 99% of threats is better than stopping 98%. Or in this case, much better than straight up allowing unknown people to root your server.
In general, a harness is something that lets your AI use tools on your computer and lets it work independently while you walk away. (Very simplified definition, not all harnesses are that automated.)
It's a long time since I tried Vibe, but when I did it was one of the worst. Back then it had broken support for MCP or computer use and other tools people now regard as near essential in AI. Hopefully Vibe is better now. Sadly Mistral are a long way behind.
But yes, it's sad that they don't release models anymore.
Thanks for the definition !
However, I also use the Mistral Vibe chat in my browser. I think they only switched to GLM-3.5 here a couple of days ago (https://docs.mistral.ai/resources/changelogs). It'd be nice if Mistral had a desktop client, but I have Goose installed which I have no real complaints about.
Captcha had me ruffled at the onset as I am slightly visually impaired and couldn't pick out the somewhat grainy images. It seems to be the standard now.