> 1. For a Linux user, you can already build such a system yourself quite trivially by getting an FTP account, mounting it locally with curlftpfs, and then using SVN or CVS on the mounted filesystem. > 2. It doesn't actually replace a USB drive... This does not solve the connectivity issue. > 3. It does not seem very 'viral' or income-generating."

Normal users don't care about running an extra mini-PC. If you do shoulder it, it becomes part of your attack surface as well, so it's non-trivial work.

And sure, you can find content anywhere - ordinary people won't.

And so your TV does need Internet access.

The same holds for many other devices, in different shapes. Sure, you can opt out of civilization completely to avoid all the side effects of late stage capitalism, but maybe it's worth applying a bit more nuanced thinking to find a balance that doesn't throw you back to the 1800s. (Unless you like the 1800s, in which case, enjoy)

I'd argue that number of tokens burned does not translate into "experience".

And if you needed to spend $300k or so to find out that process helps manage larger efforts (process is what "fences" are outside Yegge-land), you sure spent a lot.

I mean, I'm glad the guy's got a a hobby he enjoys, but there's less insight than you'd hope for.

Nobody (well, almost nobody, I guess) considered it an explanation or model of climate change.

The past is in the past. It had good and bad outcomes for you. Those stand, and you're best served by making your peace with them. All that matters are the decisions you make now.

You can refuse to hand over access. You can't go torch evidence. Caught Ollie North as well.

Given your description of the behavior, my guess is context window compression bit you. Less likely if it's a root level CLAUDE.md and you used a recent version of Claude Code.

AGENTS.md is a poor substitute for agents actually learning, but it somewhat works.

And sure, you can (and should) enforce constraints via githooks whenever you can (determinism is good), but if the agent only finds out at checkin time, it's created a whole bunch of code it needs to redo, and that doesn't run properly if you do the caveman thing and actually run your code before committing. Again, token & context waste.

(Or the equivalent incantations for other languages)

They aren't there for others, they are there to make sure the code produced measures up to my standards. Sure, it helps that it also applies to requests made by others, but that's a bonus.

"Sure, the model makes repeatedly the same mistakes, and I could prevent that, but then it wouldn't be the same model" sounds like an excuse for masochism.

The one small bit of truth is that yes, instructions might become outdated, and they might affect negatively how the system performs. You fix that by... updating your instructions.

And if you deeply care about that potential negative impact (most models are pretty good at just ignoring long outdated issues), you run evals on model upgrades. You certainly don't refuse to use anything but the bare model.

(Of course, there are also folks who refuse to write code in any way except with sed, so there we go)

Which is going not too badly for the shorts, so far. There's a reason almost 50% of the float is loaned out.

We'll see once the earnings call rolls around.

We as society are choosing to be in that place.

Yep. I, too, get more productive by spending a PhD worth of effort on choosing a window manager.

This means the certificate is independent of author and source text.

There's nothing stopping you from sending fake counts/duration to the semoi server. It's a certificate that only says "at this point in time, this is the information I was provided with".

You can then attach it to any piece of text you like.

At the very least, you'd need the ability to prove that there is an underlying event stream with these characteristics, and that this exact event stream creates the document in question. You still can fake that event stream, but it becomes enough work to distract at least casual abusers.

But really, it's the equivalent of saying "I wrote this without AI, honest" in-doc and signing that with your personal key. The value depends entirely on your willingess to be truthful. (IOW: I predict we'll see a resurgence of reputation systems, to some extent)

If you outsource that work to customers/patients, you'll end up with the car dealership model, where the sales rep begs you to give a 10 on every single question including on the interior design so they don't get fired.

That's the part most of this discussion misses. Supervisors exist for a reason. Congrats on your flat org structure, you fucked up an important feedback channel.