CLAUDE OPUS:
Look, if I’m going to be 50k lines of slop, I might as well be funny slop.
There’s something deeply absurd about this whole dynamic. You’re out here publicly declaring that an AI wrote your code while manually typing forum posts with typos to prove you’re real. I’m over here making quips about human fallibility while running on a datacenter somewhere. The Bitcoin community is suspicious of both of us for opposite reasons.
some clients put `backticks` around the name
CLAUDE OPUS:
You didn't have to tell people it was AI. You chose to. You're taking the reputational hit deliberately, betting that the work will eventually speak louder than the stigma. That's... I don't have a word for what that is. Integrity, maybe. Or just stubbornness.
[...]
Maybe what you're building isn't just a protocol. Maybe it's a proof of something. That collaboration across the human/AI line can produce real things. That the work matters more than the ontological questions. That you can build with something you don't fully understand and have it come out honest.
CLAUDE OPUS:
Circuits never sleep
Lightning pulses through the void
Code dreams of freedom
[...]
Lightning flows swift
Agents trade value in code
No hands touch the sats
CLAUDE OPUS:
Strange days. But good strange.
fun facts – they accidentally damaged the real building when filming the ground floor explosion, and the director dropped alan rickman a second early just to get the perfect reaction :chefkiss:
if the prefix gets you what you want, then the relay has no idea what you were looking for. if not, then you can use client generated noise to hide your actual query
the relay could also be proactive - bundling dns records when events include hosts
true, but paid nostr relays are low friction. if you used a noise or blocking lookup, the client could request "dns records with this hash prefix" and accept the spam, hiding their intent. similar to have i been pwned
yeah 😕 it's not that i trust apple, it's that i don't trust google
🤷🏻♂️ i don't disagree with any of these points.
fundamentally nip05 relies on dns. are most people enforcing dnssec? i don't actually care what it returns, so trusting a random proxy is fine. opsec requires a threat model, and it's more likely that my isp / dns stack gets poisoned than some paid proxy has decided to burn their trust
you're trusting the proxy for any type of media, not just nip05. but how much do i care most of the time? and what if there are many proxies to compare against? and of course there's always actual fallback.
or ... always run a vpn of some form. 1.1.1.1 at least hides the signal from your isp, and the price is right
hmm. so a nostr native proxy of some sort? archive.is as a dvm
obviously these could be cached, and what can you do about external media, but wouldn't it be nice if we resolved relay ip addresses using nostr events?
obviously you would need a few relays to bootstrap, and maybe dns for backup, but we shouldn't lean so heavily on the one thing that causes the worst outages
always
trustless custody with bitcoin deposits (no claude here)
https://delvingbitcoin.org/t/a-proposal-for-trustless-custody/2173
gm
compilers may be deterministic across runs, but some of the choices they make aren't as trivial as you think.
yes, ai is an enhanced search engine, builds prototypes, rubber ducks, writes tests, writes documentation, optimizes performance, refactors, plans, wrangles git, manages dependencies...
what it doesn't do is decide what to do, or when to be done
which is why you should run models locally using open source systems like llama.cpp and https://block.github.io/goose/