I love your insights, thanks for commenting. I’d just note that in some cases the word “nerd” has grown to mean just about anyone with competence or expertise due to their intrinsic interest & enthusiasm for the subject area. So maybe becoming an “equestrian nerd” or a “construction nerd” makes you immune to overbroad marketing claims in those areas!

I love your observations here, and applaud the good work. A few thoughts:

1. I think the problem is more complex than “switch from platform A to (better) platform B”. The reason for this is that in many ways the reason “platform B” is better (e.g. Mastodon, PeerTube) is that it is creating a forest (ecosystem) rather than a skyscraper (monolith).
2. People have become used to signing up for services at a single site, and this relationship/architecture teaches us something–that there are only two parties, “me” and “the service”. The service is almost always run by a mega corporation.
3. But in terms of human society, this is a very, very strange relationship/architecture, historically. Usually, we are part of a community. And our community is connected to and bridged with other communities. And the communities form larger and larger alliances and nations etc. The internet has “cut out” the community layer, and then fed us a topology and service that makes it look like community (e.g. Discord), as long as we follow the monolith’s rules.
4. Inevitably, like the When We Get Komooted author explains, monolithic corporate apps lose alignment with the needs of their users, and often by design enclose the community and extract value while selling the community out.
5. To avoid this, we need to re-imagine how we relate to our services–we should be thinking first in terms of picking a community, and supporting that community, and making sure our community supports the services we need, and then in terms of connecting our communities to larger and larger alliances and structures.

IMO, this is the only way to re-gain the power that we need so that we can align our services with our natural human needs, and avoid the enclosure, drift, and extraction playbooks that for-profit monoliths execute on.

And BTW I’m not against for-profit companies. I just think we have to sort out what’s best for us and put our “money where our mouth is” in building up strong alternatives.

I wonder what social media does.

This advice seems off-base to me. There is value in LinkedIn connections. But you have to make the connections outside of LinkedIn. Then it amplifies the value of those connections–you can discover that so-and-so knows so-and-so and then ask for introductions.

It also may be industry specific. I’m a software engineer, and I’ve had several employment opportunities come from these connections.

I appreciate this, thank you. You might also find this recent blog post interesting form Ink and Switch: Malleable Software

https://www.inkandswitch.com/essay/malleable-software/

I think this is the underlying philosophy of why I appreciate vibe coding’s potential.

Thank you!

Thanks. I agree there are limitations to LLMs right now (and perhaps we won’t figure out how to bolt on reliable intelligence for years to come).

I’ve been contributing to FLOSS for about 20 years. For example, if you’re curious, this project took 3 years to write by hand: https://github.com/relm-us/relm

Thanks for your thoughtful reply, I think you have some great points. It’s important that we understand, at some level, or trust. Lacking trust, we need to understand.

There are many groups in the space. Examples:

• https://openeurollm.eu/launch-press-release (European universities’ initiative to create an open weights, open source foundation model)
• https://www.deepseek.com/en (Chinese research company that made headlines when they released an open weights model of similar quality as top LLM capabilities for far less than US companies spent in training and energy. They’ve been criticized for being Chinese and gathering data from users, but that criticism only applies if you’re using their service, not their open weights model).
• https://machinelearning.apple.com/research/openelm (Apple released this model with training data)

Here’s a more complete list: https://github.com/eugeneyan/open-llms

Thanks for your kind & thoughtful answer.

This is exactly what I’m trying to do, but I was taken aback at how negative the solarpunk community took things. I thought of myself as solarpunk, but I’ve had to reconsider since posting this.

I think you could be reading into what I’m saying a bit, but I do appreciate your example as gedankenexperiment. I think what you’re getting at here is that not everyone should be empowered to code, because coding is powerful, and power can do harmful things, like genocide. Is that right?

If I read one layer further, I think what you might be most concerned with (correct me if I’m wrong) is the conveyance of statistical power in corporate hands, where decisions are often amorally arrived at, and LLMs and their training sets could represent a bad form of this–if they are allowed to be used for ill. Is that right?

I guess I just find it empowering to work on good objectives. I’m the moral agent, and I treat the computer and all of its capabilities as a tool. The AI system I have running on an old(ish) GPU in my closet is powered by solar panels, transcribing my audio notes, and giving me peace of mind that my data is within my digital domain. Adding an LLM to that GPU is part of the ongoing experiment. And if it helps my daughter (who is not a coder) build apps that are just for her and that she loves, well, I’m cool with that (see other posts for details, I have to get back to work now).

Thanks for your thoughtful reply. I admire that, despite the clear differences we might feel around the subject. I’ll try to be thoughtful as well.

LLMs are the opposite of anything ecological IMHO.

I think this is a really interesting point, and I hope to hear it unpacked some time. I’d be interested to know if you’re talking about American LLMs, or some other breed of LLMs, or the transformer algorithm that generates language models itself.

We have a thousand of those already. A better example is needed.

I mentioned this in another reply, but will repeat here a bit. I didn’t go into detail in the original post because I wanted to be brief. But the habit tracker app I was thinking about was something my daughter designed. She isn’t a coder. But she had a complex set of nuanced motivation ideas for herself–she wanted to make a system where if she didn’t something healthy for herself, she would be awarded stars, and if she did something social she would be awarded flowers. I’m doing her app a disservice by abbreviating it. She wrote a 19-page description (Product Requirements Doc, in engineering terms, but she wouldn’t know that term) in Google Docs, and then built her app in v0. She was so so excited to see her ideas come to life! It’s the first time I’ve ever seen her really interested in computers.

(re: mold an existing app) That’s not how any of this works. One more reason to shun those who do not care and take the time to understand what programming is all about.

I’m not sure what you mean here. I’m a FOSS developer. I know what open source is. I also know what it takes to start with an existing open source app and mold it into a new shape, based on new requirements that I have. What am I missing?

Linux is free FFS, install Ubuntu today and you have all the languages you’ll ever need. How is code vomit vibe coding helping? Also LLMs are very expensive to run right now, it’s the worst example.

I’m running an LLM and a transcription service (audio -> text of my notes, synced via syncthing from mobile phone to server, then processed using n8n and a docker image of whisper-asr-webservice) on an nvidia 3080 GPU in my home, powered (mostly) by our solar panels. I’m exploring new paths, and vibecoding seems like an interesting one to me 🤷

Last but not least, I hate how all the CEOs, managers, companies, and random people try to: pretend that open-source does not exist, change the meaning of the word open-source by associating it with binary blobs, and show developers as selfish people (“tech wizards”) who want to keep the technology for themselves.

I’m not sure that I agree with this statement.

You don’t want to learn how computer works and it’s fine, it’s your right, but don’t pretend it’s anyone’s fault.

I guess I didn’t think I was blaming anyone here.

My vision for the future is one where it’s more equitable–where digital algorithms don’t govern our lives like they (primarily at the hands of corporations) do today. I’m exploring what vibecoding might mean if it emancipates people to contribute to the ruleset that is often hidden from their view, especially when they don’t have computer/technical expertise (but also by just being a human being in this era, when mobile phones, social media, and unhealthy relating with devices are ubiquitous and basically just “expected” of you).

lol, that sounds like a disaster.

I’m curious, what would it look like in 300 years? What would be different, and enable a positive human-computer alignment at that time? I know you’ve said it’s out of scope, but I’m curious what we can’t have now that is desirable in the future.

lol, fair point. <3

I do hope we use it judiciously. So far, I’ve found the “biggest bang for your buck” to be at beginning a new project. But I’m also wary of vibecoding in its extreme form of “just press accept”.

Right! I guess this is precisely my point–big corporations are running with it, and so the future will be whatever they make it. But I want to make my future, which is why I’ve built solar panels on my home, built my own server, re-used old computer parts in my closet, hosted my own server, and am running a GPU with my own ollama and whisper AI algorithms on it. I’m hoping to take control and not just be a consumer of corporate enshittification.

You’re right, it’s a bit tongue-in-cheek. But it’s a fun name, and I found a lot of people didn’t understand “no code / low code” and even more didn’t really get excited about it. Vibecoding is interesting to people, I think.

You make a good point about software being potentially low capital. Open source is a great counter example.

But I wonder how do we know what people need? Are the solutions out there actually good for everyone? My daughter is not a coder, but started vibecoding her own habit tracker app last week. She’s very excited about her motivation system of stars and flowers, and the nuances of how to make it just right for her. She wrote 19 pages on a google doc describing her app. It’s almost like a requirements document, and if she had $30k I bet she could hand that document over to a software engineer and they could build a mobile app for her.

If she hadn’t built this app, I wonder how many habit tracker apps would have also advertised to her, or sold her habit data? If a person is not a software engineer, they kind of have to live with other people’s decisions in the digital sphere (and some folks, I’ve found, aren’t even able to evaluate software for safety, privacy, alignment with their values etc. let alone build it).

I guess I just wonder what the world would be like if the bar for personalized software were dropped so everyone could create just what is needed, for them, wherever they are and in whatever community they find themselves.

I might be misunderstanding, but it sounds like you’re angry at AI, or at least, you’d like it to diminish not grow in use.

We often think of “AI” as what is promoted by big corporations–but it doesn’t have to be. The math, algorithms, and machines that run AI can all be ours, and I think we can run them responsibly. For example–I run an AI transcription service just for myself on an old GPU. It works quite well. I also have solar panels installed on my home. I think it can be carbon neutral.