dpc_01234

As someone who maintains own coding harness, arguably more capable and powerful than Pi, I assure you the level of integration required to have something working really well nowadays goes against "this harness is yours" philosophy. "Codemode" completely changes the inter-workings of the harness, which spills all over everything else. And codemode is likely the inevitable future, as it's just much more efficient and powerful way for agents to do stuff. I'm planning to completely abandon non-codemode and make codemode the only "mode" in my harness as soon as open source models that I can run on my GPU can handle it well. I'm holding back as I don't want to deal with the complexity of having to support both.

> This just reads like Pi is becoming Armins and Marios opinions on what a good harness is instead of letting us build our own with the features we want and need.

Realistically it was always their harness. If you want "your own harness" you can always click the Fork button.

Nothing better than staffing your prompts/skills with long lists of all the things that you don't want, but agent might think you might want even if you didn't ask.

> I would argue that this is unpopular not only amongst retirees but everyone. And it would have tons of negative side effects.

Every tax is unpopular and undesireable.

Why would I work if government is taxing my income? Why would I invest? Why would I drive the car, blah blah.

Land tax is easy to collect, fast to pay, hard to avoid or game, and encourages productivity and efficiency.

And this cuddling of boomers who've benefited by piling up gigantic government debts and expect to be paid back (typically holding gov bond) is literally going to destroy the financial system. Part of the benefit of this tax is that if you can't pay for fair value of the land you're preventing others from using, you have to sell and get out, so e.g. a productive family can pay your for it, and use it instead of your now unproductive self. If you don't want that, you have to pay the same tax they would pay. Just because you're retired doesn't mean "your done with your duties to the rest of society and you can just expect free shit and do nothing" _especially_ that your "wealth" is just rent seeking on younger generations.

If boomers keep preventing younger generations from being productive and having opportunities, the economy will dwindle, the pile of of debt and other financial assets will collapse, hyperinfation is going to destroy their paper wealth and they will be starving or worse. Just watch, because I doubt at this point is avoidable anyway.

https://tau-agent.dev/ in my setup. Many sessions each multiagent, in different sandboxes, sending messages. Also nothing in the main article that Tau wouldn't have. I just don't have stamina for more "marketing". Async tools ... sooo basic. :D

Any Android XMPP client recommendations? I tried one, then it's fork Monocle, and none of the seem to be able to handle simple notifications correctly.

I watched the English version video and it seems to have nothing to do with "Stop Killing Games".

I wish them well, but ... just stop buying Play Station? I can understand strong consumer protection for food, medicine, healthcare, basic services, utilities. But ... video game consoles? If you don't agree with "Sony tax" ... stop being a stupid sucker and don't buy their products?

There's no point, except if you want privacy and independence. I am playing with a personal assistant that checks my emails, calendars, sends me an agenda and maintains my TODO list. I am not sending such data outside.

SelfCI: https://radicle.network/nodes/radicle.dpc.pw/rad:z2tDzYbAXxT... , supports git & jj

Thank you! It's great.

I don't think I have a "burnout", but LLMs are really exhausting due to amount of pressure they generate. No one is really pushing me to increase my workload, but at every moment there is always something ready, done by my clankers or clankers of other people that I could be unblocking. In the past (before LLMs) it was already hard to keep up, but now it feels like there's 10x more things waiting at any given time, and there could be 10x more if everyone just "optimized" and streamlined processes fed the AI even more tasks in parallel faster. It just being a bottleneck of everything, all the time is tiring...

I am happy about all the little side-projects, and ideas it help my realize, and I enjoy exploring this new world, but I've noticed LLMs feed my unhealthy "don't want to take a break and waste time being idle" mindset, and I need to correct it.

W.r.t. article's main complain - I think the similar thing happened due to factory manufacturing automation. What used to be a varied skillful craft in a shop became standing in a single place of an assembly line doing the exact same thing whole day. LLM took away the more creative and variable part of the work, and left the repetitive QA rubber-stamping. Probably some of the mitigations used back then could be rediscovered today.

Nah. My beliefs are actual truth, so if provider is shaping their models according to my preferred political narratives that's correct and only moral thing to do. Anything else would be morally bankrupt.

That's pretty much the architecture I'm using in my personal coding harness Tau (tau-agent.dev) . There are some other points in here, but there are relatively minor. I think the observation that event log / event sourcing / cqrs works perfectly for harnesses is not very novel.

Sad news. Best wishes!

From UX perspective modal editing is all I care about and I just got used to Helix. And it's very feature complete and relatively stable, so hacking it and maintaining bunch of patches is not a lot of churn in practice.

My prediction is that there will be a Cambrian explosion-like event in software practices for 5-10 years (assuming continuous broad affordability availability), because LLMs can afford us a lot of freedom in trying a lot of new things including writing new tooling and changing the process. There's a lot to explore and I guess we'll collectively see what sticks.

Author here. Here is my PoV on that evolution.

1 year ago Claude Code was relatively new, and a first polished tool that really fitted my CLI-centeric dev-views. I used Aider before, but Claude Code was just much better. The autocomplete AI coders did not seem useful, and didn't have good integrations with Helix text editor. However even the frontier models were relatively bad in practice. Useful but not trustworthy at all. Being wrong/stupid 5-10% of the time compounds quickly.

6 months ago agents became really robust at just writing code they were told to write. Around that time I started really leaning into LLM-assisted coding, which require some skill, experience and adapting own workflows and tooling. And it takes time and effort.

Right now frontier models are really productive and robust. Sure it's still a fancy-autocomplete under the hood, so one needs to plan around that, but it's more common for Slopus finds bugs in my old human-written code, than I find bugs in its new code, especially that one can now easily write and maintain tons of tests which otherwise would never get done. LLMs don't have context and good judgment, so it still takes a lot of designing and steering the agent to write the right thing, but that's OK. And as the productivity bottleneck shifted very heavily from writing code to all other thing around it, it makes it very apparent that it's not that the clanker now that needs to get better, but the process around it.

I'm currently running on a fork of Helix text editor, which I heavily gutted to replace the block cursor with a beam-style (like one in insert mode, but just all the time). Since the maintainers are drowning in PRs (472 open ATM), I understandably don't expect them to have time for my weird ideas. Then I pile on top whatever PRs I want that I find useful out of these 472, and with a little bit of LLM help I have a very different text editor than the upstream.

If you read the post till the end, I am open for lots of forms of collaboration. Its just sending chunks of code diffs around is becoming increasingly like sending diffs to resulting binaries. Just inefficient.

Yes. At this point a prompt that produces the desired result is more useful than the resulting code in a PR. Effectively the code starts to have properties of a resulting binaries.

Non-technical users might not be aware of much.

E.g. most peoples don't really think or ask that their tap water be free of cholera and other harmful substances, and yet we might want to make sure that continues to be the case. So it's not strong argument worth arguing about.

The real argument is - how much a compromise a replaceable vs non-replacable battery is. And I suspect the biggest part of non-replaceable batteries is actually superficial vanity considerations (gee, is it 7mm or 6.5mm), and planed obsolescence making more money. But the technical aspects are still a valid debate.

P2P? I have a p2p social network with a public/demo instance hosted at https://rostra.me .

OK. That's much easier. :D

I wish I had your problems. :D . Problems that are really only a mild inconvenience, and can be solved with a single line in hosts file.

My biggest and possibly only problem preventing me from going IPV6-only is that Github doesn't support it, and there's just too much darn software I need to needs Github. (Yes, I know NAT64 exist - it's just extra complexity for something that is not even my problem in the first place).

This encoding is so long, that I'm more likely to remember the raw address. :D

And I don't think I ever typed manually any IPv6 address other than `::1`.

These ad companies pay for transfer too.

Install AdNauseam if you have unmetered connection and let it download as much data from them as it can.

TL;DR: Generic uninspired anti-Wayland rant.

> In my experience, the most natural way to write things in Rust is usually the fastest (or close enough) as well.

Well, a lot of C/Odin/Zig people will point out that Rust's stdlib encourages heap allocations. For actually best performance you typically want to store your data in some data-oriented data model, avoid allocations and so on, which is not exactly against idiomatic Rust, but more than just a typical straighforward Rust just throwing allocations around.

It's slop derangement syndrome. Agreed.

Joke's on you — All my posts are written by some Slopus now.

No idea what happened, but you'd be a fool to believe anything BBC says.