If Capitalists could, and are doing, they'd make alabama be engineers if they could afford it.

It's so weird watching the tech work force go ham into the "tey terk ow jobz" rather than look at capitalism.

Man. This site is filled with weird racism.

The abstract benefits are quickly outstripped. The same way adding more highway lanes never improves gridlock. Its inducement.

We don't really have that much more good information now than 30 years ago. We had an explosion of garbage that google saw as an oppotunity to sell us on, rather than filter out.

Google saw it as their job to keep us on search longer, so the SEO garbage filling the search feed benefited them.

I guess if you're literally in a greenfield project, at the start, and it has nothing else to look at, then you're right; but everything I've been doing is taking existing stuff and improving it.

So my advice might have a bad edge case that only exists immediately. My setup is to tweak and improve on existing code bases so there's almost always something it can review, write to, read, etc that'll drive it to where I'm trying to go. So even in a greenfield project, it's start to do something rather than overthink everything. Those thought traces don't suddenly disappear.

There is the "muddled middle" of context that might get trapped in, but I don't think anything you can really do will stop that.

The only think I could think that'd be better than the --reasoning-budget would bet a budget jitter just in case it really is repeating a pattern and you want to escape it arbitrarily, otherwise yes, it could keep looping if you're always cutting at the wrong time.

the message can be some combination of tool calling, summarizing, etc. It's overthinking often is a bunch of recursion, so simply stopping t and redirecting is all you need to do.

If someones building a harness for llamacpp, you can set this per message, so it's possible to dynamically control it by watching for the expansion of the thinking traces, and redirecting it.

I use the message to tell it to use subagents, add additional logging and to use opencode's dynamic context pruning.

As such, we'll just whisper here _skill issue_.

Instead of allowing races and women into the public benefits sphere, they slowly dismantled the social safetynet.

In the specific instance for education, pushing state funding onto the city property taxes and school districts ensured impoverished areas would continue to fund impoverished schools and as the decades wore on, this tightening of budgets bled into it's surroundings and then the dismantling of funds as per-head attendence started via magnet, charter schools and now school voucher programs for private schools and the rest.

This is a pipeline designed to punish society for integration. this is "critical race theory" in the next 5 decades.

You can blame it on techno culture, but that's just the indirect cause of fundamentally desociallizing/devaluing public assets. You can make a direct association, also, with the rise of the business class as another attack on normalzing this type of segregation without laws.

No one was going to buy it in that state, great.

Nowe we have AI; in an afternoon, it'll pound out a todo app and all your choice of fixings. Great!

No one is still going to buy it; 2x, because the "total addressable market" is not the globe, because, you know, joe over there learning basic programming can do it just the same as you now. There's no secret sauce.

Whose making money? the guy selling you AI. Great, but you know, your apps not going to sell when anyone can implement any moderately time consuming app.

So not only do you have the poor business model of your todo app, you also have the poor marketability of a todo app, since any AI can do it just as well as you.

So yeah, sure, AI is building apps, but aside from selling you this wonderful capability, it's a snake eating it's own tail.

Now they can destroy the US dollar and move everything into crypto, or so they think. Who knows if the billionaires will actually understand whats happening.

There definitely going to be a lot of fortune 500 companies absolutely wrecked by the amount of changes to their code base that no one will be "responsible" for because none of the workers will really know if it was their agent that changed something.

There could be some outliers who found the correct tools at the right time, but I don't think they'll suddenly be thrust into the money, because good code is definitely not the only thing that lets people succeed.