It needs to be end-to-end encrypted.

How do you do that if you only control one end?

Asymmetric encryption? Both you (the human) and the agent publish public keys, the agent sign/encrypt the OTP request with you public key, you verify/decrypt using your private key, then do the same the other way to send the OTP (always encrypted though, given you’re sending a secret).

Something like that?

But that doesn't help for the agent receiving mail from arbitrary 3rd parties

Oh sure I assumed they meant for the OTP

You definitely need to provide evidence of use.

https://www.dreyfus.fr/en/2025/03/18/proof-of-use-in-the-uni...

Pi.dev is pretty good in giving tons of control to the use and has extensions that you can easily build.

Although people are complaining about its RAM usage in this thread, I haven't bothered to check how much RAM it uses.

I refuse to run npm slop on my hardware

Isn't the key thing with skills that the description is used to match them from a prompt that doesn't mention them?

Would a prompt library do that too?

Just like with mass-produced materials vs hand-crafted stuff, you're gonna have a lot of crap quality and rare, expensive good quality stuff.

And most people can’t just spin up a furniture factory at their whim and call themselves a designer. AI gives everybody with the slightest gumption a fully-functional, “initially plausible crap” factory at their fingertips, so everybody with actual skills gets lost in a sea of useless garbage.

Discovery is always the problem to solve - discovering the good products is hard.

And when there’s an ocean of bullshit, it’s a lot harder, which makes the incentive to do good things nearly zero. Scale is very important, here.

Luckily the same AI tools that are generating the content can be used to build better tailored discriminators for it as well. If I can define what it is I dislike about an essay, video, etc., and give it to an LLM, it can tell me whether a piece I present to it is worthwhile to consume according to my standards. This even applies to things the LLM can't generate things for that meet the same standard for its programmed/prompted discrimination.

Yeah works out great for HR departments and job hunters.

Assuming that the LLM search will be meaningfully better at cutting through bullshit than the generating model was at avoiding creating it is, charitably, dubious. Assuming that it won’t be every bit as gamable as Google results is as or more dubious.

For what?

DIY smart sensors for whatever you want to use them for

For 9.7 million, I would spend a considerable amount of time trying to recover that.

I don't even live in the same country anymore. I've looked at the files I have, and it's not there. It's gone.

> keyboard/shortcut situation is absolutely cursed. Not different...actually cursed

You know, you can change almost any shortcut you want with Karabiner (app). You don't even need to memorize them.

When I first switched to Mac after using Ubuntu for 4 years before that, I didn't expect this level of customization. It's misunderstood because Apple doesn't advertise this.

>You know, you can change almost any shortcut you want with Karabiner (app)

That's actually my other complaint. "Fixing" problems with the OS with mystery apps.

Connected an external mouse. Mouse wheel is inverted...weird? Google it. Yeah you can toggle it. Thank goodness. Apple knew people use mice. Oh but that inverts the trackpad too. WHAT? You're joking. I need to pick between a sane trackpad and sane mouse? I own both and need both to work to work in a not upside down manner.

Climb onto an AI and ask it what to do because this is insanity like surely not this can't be how it is. LLM goes yeah no that's just macos you need to install a mystery app to unfuck it.

Don't get me wrong my overall experience is positive and there has been the expected learning curve which is fine ofc, but also a fair bit of "what the actual F how are people OK with this".

This one was shocking to me too. I get the argument around the upside down trackpad, but inverting the mouse wheel with no built in open is insane. I also have a mystery app who's only just is to correct this stupid behavior.

Building a tool to help review changes made by AI agents in response to PR review comments.

The key functionality is to be able to easily see the changes made for each comment, rather than each file.

I like the idea of tying the products to the companies but just make two categories: Indie (default) and Big companies.