I would be up for the challenge of self hosting, I think. I have considered building a home lab for many years, but haven’t been able to save up, nor taken the time to browse the local used market. I just don’t know too much about it, so I figured I’d ask how involved you meant the solution should be.

But you’re right that it’ll be a huge obligation for me. I think my main objection is that, even if I get everything right with self hosting, it would depend on something in my home. If I ever leave the neighbourhood permanently, I wouldn’t want to self host for this group I don’t know or meet with.

My only problem with options like librebit is that I probably couldn’t justify the running cost (vs. free for Google Sheet) to a group that wouldn’t see the value keeping the data off these tech companies’ free servers

Thanks for the heads up, I feel like I already started down this path when I objected to using Telegram for informal communication

Thanks for at least mentioning it:) I’ll look into it

I appreciate the advice, and I considered it as well, but I think it wouldn’t fly in 2026 when everyone expects wireless communication from the couch

Makes sense. I also really like that I don’t become an access point. Say if I move some day, there would need to be someone to take over.

Do you have experience using Nextcloud’s servers for this? Do you think it would be something the average Joe could handle in case of me not being able to do it?

Thanks:) I’ll try to read up on self hosting nextcloud, but it seems like a good alternative.

Also, a wiki? I’m probably just thick, but how do you suggest we do shift management and such?

Thank you!:)

I must live under a rock - I’ve never heard of this before. Do you suggest I just set this up on my PC at home and just have it running all the time?

I don’t have a homelab or similar, and in this economy not really the money to fork out for AI-caused inflated hardware prices for building one

If your tactics disrupt the order of things under capitalism, you may well be accused of violence, because “violence” is an elastic term often deployed to vilify people who threaten the status quo. Conditions that the state characterizes as "peaceful’ are, in reality, quite violent. Even as people experience the violence of poverty, the torture of imprisonment, the brutality of policing, the denial of health care, and many other violent functions of this system, we are told we are experiencing peace, so long as everyone is cooperating. When state actors refer to “peace,” they are really talking about order. And when they refer to “peaceful protest,” they are talking about cooperative protest that obediently stays within the lines drawn by the state. The more uncooperative you are, the more you will be accused of aggression and violence. It is therefore imperative that the state not be the arbiter of what violence means among people seeking justice. In the past, activists frequently leveraged the violence of police, taking actions they believed police would likely respond to with violence, in order to expose the brutality of policing and force the public to witness and confront it. Many of those actions, including protests carried out by the Southern Christian Leadership Conference or the Student Nonviolen Coordinating Committee during the civil rights movement, took place in a context that was very different from today’s world of pervasive mass media. Today, people are much more accustomed to witnessing violence, including violence against protesters, as such imagery is shared widely on a regular basis, particularly through social media. The public has largely become inured to such imagery. The violence of the state in response to protest is rarely scrutinized to the degree that protesters are scrutinized. The idea that if you are defiant in the face of authority you should expect to incur its wrath is firmly entrenched in our culture. When people who defy police are abused, we often hear people ask, “What did they think was going to happen?” The ubiquity of the abuse puts the onus on the abused to avoid it, because they simply “should have known better.” Protesters are expected to remain “nonviolent” at all times, regardless of the circumstances, while the state is assumed to be justified, at leas sometimes, in inflicting violence to quell “unrest.”

What is “better” and what is “100% better”?

I feel like most other European languages I have heard do not either. (Well, what is “proper” anyways?) Care to share a language that does?

Do most countries’ education systems include a lot of propaganda? I have a hard time discerning between a general claim or US defaultism

Spot on. Some countries in Europe do this already, although it is controversial.

Thank you!

I think we disagree on the nature of a tool. Or maybe I am thinking about more than a “tool”, but not using the appropriate word for it.

Image riding a very fast horse. There is no perfect repeatability, it might veer off, or react to something you didn’t see, but a good rider would probably manage to arrive at the intended destination. I think I view it the same with agentic coding.

Now, I agree a horse is not a tool, and that’s why I mentioned that my language is perhaps a bit imprecise. (I guess you could even call it an agent.) But maybe an “instrument” or an “implement” fits, although that’s a bit cold wording for a horse in general, as they have other qualities, as being cute etc… But I think you get my point.

I very much think LLMs can fall under the description of “useful implement for coding” today. But I do think it is a very poor knowledge retrieval implement. In fact I sucks for all these one-off questions, I my opinion.

I think the more interesting discussion is about how these AI companies consolidate power even more, how they steal data, how they pollute like crazy. But I think people who dismiss their use in coding perhaps view LLMs more like a flashlight and less like a very fast horse moving you from A to B.

Following my analogy with the archer, promting the right way is like accounting for wind. And again, no matter how much the best archers in the world account for wind, they do sometimes miss. Still very impressive how high their skill is, even with randomness involved. And with agentic coding, one can always shoot twice.

I both agree and disagree.

As for having little control, I feel like that happens in other disciplines too. The best archers need to account for the stochastic nature of wind patterns, and thus they do not always hit their intended target. But still, their accuracy is far greater than a novice. There is both skill and “luck” - if you will - involved in the process. You definitely can hone a skill you have little control over in the beginning, I believe. Maybe this is the analogy that should’ve been made.

I will say, “knowing how to prompt” feels like a weird skill, and I think the way we interface with these tools is kinda wacky. Regular text feels to fuzzy.

But it does help immensely, I find, to take every wrong agentic coding output as a learning experience. When I know the answer, and the agent failed, I ask myself why it didn’t fint it. Taking these opportunities has led me to be more proficient in the use of skill files, agent files, subagents, context window management, etc., all which have improved the agents output massively. I feel like a year ago, it was just prompting and copy-pasting (at least for me), but now, with tools like OpenCode, I can get a better looping effect with fewer errors.

I am curious about your findings

Take it easy. And don’t just take my one comment as anecdotal evidence of reading comprehension. I will say, first off, I wrote the above shortly after waking up - perhaps not my most analytical piece ever. Furthermore, English is not my first language (kinda not even second). And finally, I have dyslexia, so I literally have worse than average reading comprehension skills.

Also, from my device, it seems only the first 2 paragraphs are in quotation, and everything after “yes” has regular formatting, which gave me the impression of that being the commenters own words, and with the weird line breaks. (I’ll add I know people who have typed like that but have switched, hence I made the remark.)

All I want to say is you shouldn’t use my misunderstanding of the comment I replied to as any evidence of general reading comprehension. It shouldn’t be. And you seem overly affected by this.

Yeah I think you’re right, when it comes to AI as a coding tool. I heard someone ask something like “where on the scale from flashlight to violin would you put LLM tools for coding”. By that, they meant, if you use a flashlight, and it doesn’t work, you’re pretty sure it’s not your lack of experience with the tool - the tool is just broken. But if you play a violin and it sounds like shit, it’s probably because you’re not versed enough to play it (or at the very least you don’t know if it’s you or the violin who’s at fault), assuming you don’t play the violin.

If one finds LLMs unhelpful for coding, is it them not knowing how to play it, or is the tool inherently broken? It’s very arrogant to believe one is so knowledgeable about a tool, one which is in constant development too, that it is not them who is using it wrong, but rather the tool that is wrong.

There’s a plethora of other areas of just criticism of the technology, but I think how useful it is for coding is not one of them.

Aside: your “manmade” line breaks make your comment harder to read on a phone. I guess it’s a hard habit to break, but I would suggest you try. Most places people type text to be read by other these days, one should account for vastly different resolutions and aspect ratios (e.g. vertical & horisontal monitors). Adding in line breaks where it looks good on your screen is like writing text for yourself to read. That’s my personal opinion at least

What limitations were you thinking of?

I agree with you, but just wanted to point out maybe they were calculating with the halftime break, so 45+15+45=105 and added some average extra time to get to their number