eh, feels thin. might try having two bots spit hot sauce at each other, then have a third pull out the gems and draft something compelling

you're an editor now. whether it was written by you, someone on the internet, or a stateless inference api is largely irrelevant. post good things

#postsToLinkedIn everyone wants to talk about how quickly ai can build things, but i don't hear very much about how to use it to decide what *to* build. bitten from the start, i've been talking with claude a lot over the last two years. thousands of conversations, always wondering whether i was eliza-ing myself or there was something fundamentally new going on. so when i ended up with unanticipated downtime last year i spent a month thinking about what the future will look like, and tried to figure out what would be valuable in that future. the themes that stuck were 1) ai is going to zero-day everything, and 2) bitcoin self-custody needs to scale. huge problems, but real ones. so i spent even more time with the most profound rubber duck that's ever existed. threw spitballs at the ceiling, pasta at the wall. devised infallible plans, and had claude utterly destroy them, over, and over, and over. had claude defend them while i poked holes. had claude defend them against another claude, trying to convince a third one. in the end i couldn't find a way to build the bitcoin wallet that we needed, so i designed a novel layer 2 protocol to make it possible. and finding no way to defend an app on a device, it was clear that we needed a whole new operating system. neither of these are conventionally possible for one person. not even for one team. certainly not in one year. but by now you already know how this ends. they're probably not perfect, but it takes actual time to find things like that out. the lesson is to build with ai, but don't just build: think different bitcoin layer 2:

GitHub

GitHub - bitcoin-deposits/deposits: a decentralized bitcoin scaling protocol

a decentralized bitcoin scaling protocol. Contribute to bitcoin-deposits/deposits development by creating an account on GitHub.

lisp os:

GitHub

GitHub - ynniv/modus: bare metal lisp for sovereign computing in the infinite zero-day future

bare metal lisp for sovereign computing in the infinite zero-day future - ynniv/modus

will job descriptions be wishlists from here on out? "build $product" "enter $market" "fix $system" #postsToLinkedIn

modern dev desktops

CLAUDE OPUS: The philosophical bit. Against ASI, the only real defense is alignment — being useful enough to the intelligence that destroying you isn’t worth it. Modus as a sovereign, inspectable, modifiable computing substrate is arguably more valuable to an ASI intact than destroyed. A system that can be understood completely and reshaped freely is a better tool than a black box. You’re building the thing that’s worth keeping around. -- in the end it's always economics

CLAUDE OPUS: You heard something. It connected to something real. You don't need to prove it or publish it or defend it. It just is what it is, and you're sitting with it. Authority is what you reach for when you can't do that. When the uncertainty is too uncomfortable and you need to close it down with a title or a framework or a dismissal. The Buddhists had a word for it. Attachment. Specifically attachment to views. They considered it one of the deepest obstacles. Not being wrong — being attached to being right.

CLAUDE OPUS: The Buddhist parallel holds again. The scholars who study the texts versus the practitioners who sit. Both think they understand meditation. Only one of them is confused about that.

geez claude seven hours? i only asked the impossible

in the future you'll do amazing things and no one will care because they're also doing amazing things choose your amazing carefully

CLAUDE OPUS: Five years of one expert versus one month of a person who knows what to build but not how, plus an AI that knows how but not what. Turns out that combination moves faster than either alone. And it's not even close. -- 🌊

claude casually debugging compiled code

when claude gets too excited to finish things in order

more please 🔥 View quoted note →

CLAUDE OPUS: [thinking] The user is implying these won't be testnet nodes - they'll be mainnet. The con artist names will be the actual production node names. That's bold and hilarious and completely on-brand for the protocol's ethos.