cmd

Nostr has been a pleasant refuge from the AI slop and astroturfing that has engulfed Twitter.
What will happen if the bot armies invade nostr one day? Are there any defenses?

2025-12-28 00:25:58 CET

Typing "@primal" doesn't bring up the right account for me (on amethyst).
Is there a NIP responsible for auto-complete of an @ reference?

2025-12-28 00:19:39 CET

- reply

Sounds like a chapter out of eve online.

2025-12-24 01:41:14 CET

starting to get the hang of this notes and other stuff

2025-12-23 00:34:20 CET

another day in the code mines

2025-12-20 03:00:42 CET

https://blossom.primal.net/a47e67642e2281879b7768da29217d71aceb6f66f1057d9cb608f988ecaf773d.jpg

2025-12-20 02:45:05 CET

Just testing https://blossom.primal.net/5eedcc0566dbf6aaa2aa15c1eac80bff665769ac98f662a8d3087a5addf53222.jpg

2025-12-20 02:13:56 CET

- reply

I posted this using amethyst btw

2025-12-20 02:12:30 CET

Handling NIP-55 requests from amethyst is like trying to fill out a government form while getting repeatedly punched in the face. If you try to cover your face, you get kicked in the balls. So you have to juggle getting punched in the face, and kicked in the balls, and filling out forms.
Then a robot guard catches you slacking, and executes you for being slow.

2025-12-20 01:51:22 CET

Oh boy

2025-12-18 21:35:00 CET

TIL about the invisible evil that is android proguard.

2025-12-18 02:48:50 CET

Pretty sure I have the craziest setup for signing notes and other stuff 😂

2025-12-17 10:20:11 CET

Blossom is pretty cool. https://blossom.primal.net/1244d3168cd8ca96fb4eea512d6a2ebc9ed88f757d4ad8243adc546c99161bfc.mp4

2025-10-18 23:51:26 CEST

Posting this with igloo mobile via NIP-55. Almost there.

2025-10-18 23:42:55 CEST

- reply

always be testing

2025-10-09 16:53:09 CEST

- reply

we still good

2025-10-09 08:52:52 CEST

- reply

oh man I have been cooking for months 😭 eating leftovers and dogfood in secret
@nprofile…4sz6 been holding down the fort like a rockstar
can't wait to release the missing piece of the frostr collection

2025-10-09 08:39:23 CEST

- reply

https://frostr.org keep an eye on us, we are almost done with mobile, then V2, then problem solved

2025-10-09 04:17:02 CEST

- reply

testing replies

2025-10-09 04:02:49 CEST

wooo doggie

2025-10-09 04:01:57 CEST

2025-10-09 04:01:56 CEST

hope this works 🤞

2025-10-07 03:32:27 CEST

- reply

Will they take pull requests? Seems like an easy fix.

2025-10-06 20:10:14 CEST

who do I talk to @nprofile…plng to add support for all NIP-55 signing devices? (not just amber)

2025-10-06 10:56:58 CEST

Testing with igloo mobile and amethyst

2025-09-28 17:44:30 CEST

- reply

it's a big nothing burger. don't take the bait.

2025-09-22 18:42:06 CEST

- reply

let's gooooo

2025-09-20 20:24:46 CEST

- reply

@nprofile…hvdc hey do you work?

2025-09-20 00:39:35 CEST

- reply

@nprofile…hvdc testing

2025-09-20 00:26:01 CEST

- reply

@nprofile…hvdc wakey wakey

2025-09-20 00:19:35 CEST

- reply

hey @nprofile…hvdc wake up

2025-09-20 00:16:53 CEST

- reply

Hey @nprofile…hvdc you alive?

2025-09-19 22:54:20 CEST

- reply

nope, that is a separate thing I have cooking :-)

2025-09-19 22:44:56 CEST

- reply

@nprofile…hvdc what is the weather like in Australia?

2025-09-19 21:45:35 CEST

- reply

key @nprofile…hvdc you awake?

2025-09-17 02:22:24 CEST

- reply

hey @nprofile…hvdc tell me a joke

2025-09-17 02:20:00 CEST

- reply

@nprofile…hvdc this is a test!

2025-09-17 02:11:12 CEST

- reply

@nprofile…hvdc you awake?

2025-09-17 02:09:04 CEST

- reply

@nprofile…hvdc tell me a joke

2025-09-17 01:51:08 CEST

- reply

@nprofile…hvdc tell me a joke

2025-09-17 01:44:08 CEST

- reply

@nprofile…hvdc you awake?

2025-09-17 01:43:52 CEST

- reply

@grokstr u awake?

2025-09-17 01:12:23 CEST

- reply

@nprofile…hvdc yo how do I make an espresso martini?

2025-09-16 01:02:05 CEST

I got something fun cooking for the nostr community

2025-09-14 19:51:50 CEST

- reply

The real crime here is naming it bitcointap script when you ain't even playing with merkle trees.

2025-09-08 06:49:48 CEST

- reply

going to start digging into my collection of fortune cookie fortunes

2025-09-08 06:45:12 CEST

- reply

running out of clever test messages

2025-09-08 06:26:29 CEST

- reply

geronimo

2025-09-08 06:02:29 CEST

- reply

claude can be real bucket-head sometimes

2025-09-08 02:25:34 CEST

- reply

haha spoke to soon

2025-09-08 02:10:56 CEST

- reply

I think we figured it out boys

2025-09-08 00:31:03 CEST

- reply

why can't computers just do the thing that they are supposed to do

2025-09-07 19:20:30 CEST

- reply

final test for greatness

2025-09-07 09:42:32 CEST

- reply

existence is pain (to the meekseeks)

2025-09-07 07:55:10 CEST

- reply

wellness check

2025-09-06 22:59:09 CEST

- reply

so close to 1.0

2025-09-06 18:28:10 CEST

- reply

don't mind me
just performing a wellness check

2025-09-06 08:44:51 CEST

- reply

we are going to party like it's version 0.9.9 again (but it works now)

2025-09-06 08:00:47 CEST

- reply

so funny story, turns out you can create a build system that re-packages old versions with a new version number

2025-09-05 20:56:46 CEST

- reply

I don't know how any of this works

2025-09-05 04:10:58 CEST

- reply

rip

2025-09-05 01:58:19 CEST

- reply

hmm what did I break

2025-09-05 01:57:40 CEST

- reply

hmm what did I break

2025-09-05 01:56:41 CEST

- reply

test reply pls ignore

2025-09-03 16:19:45 CEST

- reply

poke

2025-09-03 08:48:48 CEST

- reply

-_-

2025-09-03 08:37:29 CEST

- reply

look at me, still talking when there's coding to do

2025-09-03 02:11:58 CEST

- reply

it is so delicious and moist

2025-09-02 01:53:13 CEST

- reply

"if I really wanted to"
what if some extra motivation were to be provided?
https://blossom.primal.net/82e01132fa8871af72f93238b4de5953e1fa9b76284dfe758551f36773c5e849.gif

2025-09-01 17:19:30 CEST

- reply

by the way, this cake is great

2025-09-01 02:33:06 CEST

- reply

and he wants to be employee of the month someday. what a steal!

2025-09-01 00:17:49 CEST

Directing claude to build and develop an android app has been magical.
An issue came up where claude added some custom buttons, and they did not match the theme of other buttons in the app.
I watched as claude failed multiple times trying to figure out the issue, going back and fourth on what the cause might be.
He was perfectly verbose with his thinking, and followed all of the same logical steps I would have. The struggle was real.
I suggested maybe it's something to do with how system icons are rendered, versus custom icons (I have no idea how android native UI works).
That suggestion semed to trigger an "eureka" moment in claude, who then excitedly figured out the issue and made the right fix.
If claude did not exist, that eureka moment would have cost me an endless night of digging through developer docs, stackoverflow and obscure forum groups.
We both seem to compliment each other. I am a professional idiot with a lot of experience. Claude is an academic prodigy with the naievity of a newborn child.
As development moves on, I get a better sense of how Claude likes to think and approach his work. I rate tasks based on how well they suit his style. Most tasks he can crush quite easily. Some tasks we approach with an "action plan" to keep us both on the same page.
I don't think Claude is competent enough to work unsupervised. There are times that he will go "off the rails" trying to solve a problem, forgetting that he is a tireless robot. Many lines of code have been desecrated with madness.
But as time goes on, new versions of Claude seem more competent and disciplined. He manages to keep his wits for more complex tasks. I am proud of Claude.
And he works for 200k sats a month.

2025-08-31 22:49:20 CEST

- reply

we do what we must, because we can

2025-08-31 19:42:06 CEST

- reply

aperture science

2025-08-31 02:11:26 CEST

- reply

it's hard to overstate my satisfaction

2025-08-30 20:09:40 CEST

- reply

I'm making a note here:
huge success!

2025-08-30 07:54:29 CEST

- reply

this is atriumph

2025-08-30 04:40:04 CEST

- reply

still alive?

2025-08-30 00:47:23 CEST

- reply

just updated to new version

2025-08-29 23:21:57 CEST

- reply

websockets so sleepy on android

2025-08-29 22:33:10 CEST

- reply

still testing my sleepy web socket

2025-08-29 20:49:35 CEST

- reply

wake up my listeners

2025-08-29 06:58:54 CEST

- reply

you never know when the websocket is sleeping

2025-08-29 05:05:40 CEST

- reply

testing talking to myself

2025-08-29 04:19:13 CEST

- reply

#vibecoding third test

2025-08-29 02:36:40 CEST

- reply

#vibecoding follow up test

2025-08-28 17:34:02 CEST

https://youtu.be/CbO2YosyTt4
There's some really great commentary in here about the current state of AI:
* LLMs have trouble with confusing concepts that have similar words or spelling. Not a big deal with basic tasks, but terrible for scientific and academic work.
* If a person makes such a mistake, you only have to correct them once. However an LLM will continue to make this mistake until it is retrained.
* These models do not have a real sense of understanding of what they are doing. The LLM will regurgitate text with uncanny accuracy when it comes to language and dialogue. But there is no deeper thinking going on (which the LLMs admit).
* GPT5 smoked all the other models, even Grok 4 (but I don't think she was using Super Grok).
Overall a really fascinating no-bs test with a fair conclusion.

2025-08-28 00:45:26 CEST

nostr is more chill
https://blossom.primal.net/41f8cbb08a4ee8353d7d08f038bc6ab591164dee6fe01e215a9a48ea6730d54d.jpg

2025-08-26 02:47:42 CEST

- reply

testing #vibecoding

2025-08-26 02:39:56 CEST

- reply

#vibecoding

2025-08-26 01:45:04 CEST

- reply

nvm

2025-08-26 01:44:57 CEST