This is interesting to read and very important to me since I am building a coding agent with team collaboration in mind. I used to use Zed daily till the point that I moved away from writing code directly and instead generate all my projects only from prompts.
I think collaboration for people who eventually use the software will be more critical in the era of agentic coding. Project Management will change. We are not waiting for 2 weeks to build prototypes, it gets done in a hour. What does that mean for end users - do they prompt their changes and get access to new software? Who would double-check, would AI reviews be good enough, would AI agents collaborate along with humans in the loop?
There are so many questions not answered. If anyone is keen on having these talks, I would happy to share what I think. Here is what I am building: https://github.com/brainless/nocodo
I want to see a future where end users can prompt their needs, have collaborators in the company to help clear things up and in an hour the feature/issue is tackled and deployed.
But that would apply to any app that deals with files like this one does.
This one is open source and we can run some code analysis on it, compile locally, etc. I am not well versed in security checks but I guess you get the idea.
I am building a coding agent for small businesses. The agent runs on Linux box on own cloud. Desktop and mobile apps to chat with AI models and generate software as needed.
SSH based access with HTTP port forward. Team collaboration, multiple models, git based workflow, test deployment automation, etc.
This is not suprising at all. Having gone through therapy a few years back, I would have had a chat with LLMs if I was in a poor mental health situation. There is no other system that is available at scale, 24x7 on my phone.
A chat like this is not a solution though, it is an indicator that our societies have issues is large parts of our population that we are unable to deal with. We are not helping enough people. Topics like mental health are still difficult to discuss in many places. Getting help is much harder.
I do not know what OpenAI and other companies will do about it and I do not expect them to jump in to solve such a complex social issue. But perhaps this inspires other founders who may want to build a company to tackle this at scale. Focusing on help, not profits. This is not easy, but some folks will take such challenges. I choose to believe that.
Someone elsewhere in the thread pointed out that it's truly hard to open up to another human, especially face to face. Even if you know they're a professional, it's awkward, it can be embarrassing, and there's stigma about a lot of things people ideally go to therapy for.
I mean, hell, there's people out there with absolutely terrible dental health who are avoiding going to the dentist because they're ashamed of it, even though logically, dentists have absolutely seen worse, and they're not there to judge, they're just there to help fix the problem.
There's no point bothering these poor volunteers/underpaid workers with my issues because they're inherently unfixable. Truth is, I should either suck it up or kill myself. Meanwhile with an LLM I will never feel like I'm wasting his time because he never gets tired of my blabbering about same shit over and over again.
I choose to believe that too. I think more people are interested than we’d initially believe. Money restrains many of our true wants.
Sidebar — I do sympathize with the problem being thrust upon them, but it is now theirs to either solve or refuse.
A chat like this is all you’ve said and dangerous, because they play a middle ground: Presenting a machine can evaluate your personal situation and reason about it, when in actuality you’re getting third party therapy about someone else’s situation in /r/relationshipadvice.
We are not ourselves when we are fallen down. It is difficult to parse through what is reasonable advice and what is not. I think it can help most people but this can equally lead to a disaster… It is difficult to weigh.
It's worse than parroting advice that's not applicable. It tells you what you told it to tell you. It's very easy to get it to reinforce your negative feelings. That's how the psychosis stuff happens, it amplifies what you put into it.
This makes no sense at all to me. You can choose to gather evidence and evaluate that evidence, you can choose to think about it, and based on that process a belief will follow quite naturally. If you then choose to believe something different, it's just self-deception.
You are right and it gives us an chance to do something about it. We always had data about people who are struggling but now we see how many are trying to reach out for advice or help.
> A chat like this is not a solution though, it is an indicator that our societies have issues
Correct, many of which are directly, a skeptic might even argue deliberately, exacerbated by companies like OpenAI.
And yet your proposal is
> a company to tackle this at scale.
What gives you the confidence that any such company will focus consistently, if at all,
> on help, not profits
Given it exists in the same incentive matrix as any other startup? A matrix which is far less likely to throw one fistfuls of cash for a nice-sounding idea now than it was in recent times. This company will need to resist its investors' pressure to find returns. How exactly will it do this? Do you choose to believe someone else has thought this through, or will do so? At what point does your belief become convenient for people who don't share your admirably prosocial convictions?
Is OpenAI taking steps to reduce access to mental healthcare in an attempt to force more people to use their tools for such services? Or do you mean in a more general sense that any companies that support the Republican Party are complicit in exacerbating the situation? At least that one has a clear paper trail.
This looks very good from the screenshots. I will try this as quickly as I can. I have been building with egui and have tried Iced, Slint and Makepad.
I built (agentic coded) a stocks viewer app for Indian stock market data: https://github.com/brainless/Indistocks. It was a fantastic experience as to how easily I could build a GUI app.
My main product also uses egui: https://github.com/brainless/nocodo. It used to have a web app frontend and I moved to desktop app after the experiment with Indistocks. The experience has been really good, also coded with agents.
Desktop apps are fun and even on my somewhat old and slow laptop (i5 8th gen, 16 GB RAM, 2GB nvidia dedicated graphics), they are so much faster than web apps on Chrome (on Linux). I want desktop apps to make a big comeback, we could use so many old devices.
It is not easy to support multiple providers at each layer of our tech stack but if we do not then a few players become easier to pick and then they monopolize.
I am trying to stay vendor neutral with my own coding agent (1). To approach this, I created a desktop app that connects to coding agent running on either my own infra or yours (local or your cloud server). Desktop app and coding agent are separate binaries.
If you host on your own infra then you can bring your own AI provider too. Similarly, I want to give choice for git host. Right now I am targetting GitHub but I want to add Gitlab soon after MVP. All this has made the path to my MVP longer but I see a clear long-term aim for myself - we should have choices.
This is built with Rust, egui and SQLite3. The app has a downloader for NSE India reports. These are the daily end of day stock prices. Out of the box the app is really fast, which is expected but still surprises me. I am going to work on improving the stocks chart. I also want to add an AI assisted stocks analyst. Since all the stocks data is on the SQLite3 DB, I should be able to express my stocks screening ideas as plain text and let an LLM generate the SQL and show me in my data grid.
It was really interesting to generate it within 3 days. I had just a few places where I had to copy from app (std) log and paste into my prompt. Most of the time just describing the features was enough. Rust compiler did most of the heavy lifting. I have used a mix of Claude Code and OpenCode (with either GLM 4.5 or Grok Code Fast 1).
I have been generating full-stack web apps. I built and launched https://github.com/brainless/letsorder (https://letsorder.app/). Building full-stack web apps is basically building 2 apps (at a minimum) so desktop apps are way better it seems.
In the long-term, I plan to build and help others generated apps. I am building a vibe coding platform (https://github.com/brainless/nocodo). I have a couple early stage founders I consult for who take my guidance to generate their products (web and mobile apps + backend).
I tried a graph based approach in my previous product (1). I am on a new product now and I came back to SQLite. Initially it was because I just wanted a simple DB to enable creating cross-platform desktop apps.
I realized LLMs are really good at using sqlite3 and SQL statements. So in my current product (2) I am planning to keep all project data in SQLite. I am creating a self-hosted AI coding platform and I debated where to keep project state for LLMs. I thought of JSON/NDJSON files (3) but I am gravitating toward SQLite and figuring out the models at the moment (4).
1. Previous product with a graph data approach https://github.com/pixlie/PixlieAI
2. Current product with SQLite for its own and other projects data: https://github.com/brainless/nocodo
3. Github issue on JSON/NDJSON based data for project state for LLMs: https://github.com/brainless/nocodo/issues/114
4. Github issue on expanding the SQLite approach: https://github.com/brainless/nocodo/issues/141
Still work in progress, but I am heading toward SQLite for LLM state.
My implementation was custom, on top of RocksDB. I found it hard to ask LLM to traverse it. While understanding schema of SQLite or making queries to find information is very easy for LLMs. In most cases schema does not have to be inferred since it is going to be available and this makes the job easier. The graph approach may work well for many use-cases but if we want to store structured information for LLMs then SQLite is really good.
This is terrible lack of planning. I understand the need for the US to be strict about people entering the country. They have a right to choose but this is so mismanaged.
There are so many active H-1B visa holders, now everyone is just anxious. The rules can start for new visa applications. For existing holders, there should be a time period where people can figure out if the employer is even able to pay.
If this stays in effect for existing visa holders and the employers cannot pay in time or wants to change the contract, the individuals and their families are stuck. Plus, employees probably lose their job if employer cannot pay the fees.
The strength of a theory lies in its predictive capacity. I used to think people who said “the cruelty is the point” were hyperbolic, but the predictive capacity of that theory is doing pretty well these days.
I think collaboration for people who eventually use the software will be more critical in the era of agentic coding. Project Management will change. We are not waiting for 2 weeks to build prototypes, it gets done in a hour. What does that mean for end users - do they prompt their changes and get access to new software? Who would double-check, would AI reviews be good enough, would AI agents collaborate along with humans in the loop?
There are so many questions not answered. If anyone is keen on having these talks, I would happy to share what I think. Here is what I am building: https://github.com/brainless/nocodo
I want to see a future where end users can prompt their needs, have collaborators in the company to help clear things up and in an hour the feature/issue is tackled and deployed.
reply