Nostr Web Client

Dear Nostr,

there are no solutions, only trade-offs. But we can still have lots of fun along the way.

So I was listening to nostr:nprofile1qyt8wumn8ghj7etyv4hzumn0wd68ytnvv9hxgtcpz4mhxue69uhkummnw3ezummcw3ezuer9wchszxthwden5te0wpex2mtfw4kjuurjd9kkzmpwdejhgtcprpmhxue69uhhyetvv9ujuer9wfnkjemf9e3k7mf0qyd8wumn8ghj7ur4wfshv6tyvyhxummnw3ezumrpdejz7qpqdergggklka99wwrs92yz8wdjs952h2ux2ha2ed598ngwu9w7a6fsce9rzs and nostr:nprofile1qy2hwumn8ghj7un9d3shjtnyv9kh2uewd9hj7qg3waehxw309ahx7um5wgh8w6twv5hszxnhwden5te0wpuhyctdd9jzuenfv96x5ctx9e3k7mf0qyghwumn8ghj7mn0wd68ytnvv9hxgtcqyqnxs90qeyssm73jf3kt5dtnk997ujw6ggy6j3t0jjzw2yrv6sy22vuwtly talk about replicating content across relays this morning, and so I wrote replicatr:

https://github.com/coracle-social/replicatr

Replicatr is a daemon which listens to one or more indexer relays for `kind 10002` events. When it detects a change in any user's relay selections, it uses negentropy to sync that user's notes to their new relays based on the outbox model.

The neat thing is you don't have to run one. I deployed one this morning which points to indexer.coracle.social, so if your metadata gets published there (or to any of the relays that it mirrors), you're already covered (unless your new outbox relay rejects replicatr's publishes).

No Solutions 2mo ago

👀

No Solutions 2mo ago

👀

nostr:nevent1qqsqgr8zmnpajwwzfjddya328g6qmpwm7ndel9y7w2jdcqnanpln8ucpz4mhxue69uhhyetvv9ujuerpd46hxtnfduhsygyhcu9ygdn2v56uz3dnx0uh865xmlwz675emfsccsxxguz6mx8rygpsgqqqqqqsyq2xus

Replying to

Pete Winn 🔆

I have a feeling we’re going to build a lot more than 5 cashu apps.

Hopefully everyone gets their own app. I have a plan.

And i think it’s just about grug brained enough to work…

nostr:nevent1qqs99ep9aetj0tlmces99928r4nt9tuduf9q28353eqcdr3tukc6w5qpzemhxue69uhhyetvv9ujuurjd9kkzmpwdejhgvtm0xq

No Solutions 2mo ago

No Solutions 2mo ago 💬 1

13: The Linux of Social Media

https://haven.sovereignengineering.io/e256db47fb840f116395e36ddb9dee41b17ac884602b2fdb028d056db00d1956.m4a

#NoSolutions

No Solutions 2mo ago 💬 2

12: The Windy Lawnmower Stuff

https://haven.sovereignengineering.io/5b28e6fddd03815a3d3a1df1cbe3d80929e3384038daac6c20838721b8079073.m4a

#NoSolutions

Replying to

Pete Winn 🔆

For ideology it does matter who controls your system prompt?

As a quick experiment over coffee this morning I took that last episode of nostr:nprofile1qyxhwumn8ghj7mn0wvhxcmmvqy0hwumn8ghj7mn0wd68ytn9d9h82mny0fmkzmn6d9njuumsv93k2qpqn00yy9y3704drtpph5wszen64w287nquftkcwcjv7gnnkpk2q54svljnn3 , generated a transcript and ran it through a dialogue agent that runs a 10 round discussion between pre-programmed AI agents around a given prompt.

In this case it was "What is the Underlying Philosophy of Sovereign Engineering based on this discussion between nostr:nprofile1qyxhwumn8ghj7e3h0ghxjme0qyd8wumn8ghj7urewfsk66ty9enxjct5dfskvtnrdakj7qpql2vyh47mk2p0qlsku7hg0vn29faehy9hy34ygaclpn66ukqp3afqta478g and nostr:nprofile1qy28wue69uhnzv3h9cczuvpwxyargwpk8yhsz3rhwvaz7tmed3c8qarfxaj8s6mrw96kvef5dve8wdrsvve8vvehwamxx7rnwejnw6n0d3axu6t3w93kg7tfwechqutvv5ekc6ty9ehku6t0dchsqgrwg6zz9hahfftnsup23q3mnv5pdz46hpj4l2ktdpfu6rhpthhwjv0us2s2 "

Usually I run most things on Claude 4 Sonnet as it s great general purpose model, but i was surprised at how it seemed to crowbar into the conversation a bunch of AI safety viewpoints and ideologies that aren't necessarily in the source transcript.

So I figured lets change out the model for the dialogue agents to Grok-4 and see what it does instead - does the ideology leak out still? Is it different?

I actually think that Grok 4's first assessment kinda nailed it:

> Sovereign Engineering seems like a mindset or movement for building tech in a way that's deeply human-centered, decentralized, and empowering—think vibing with AI and open protocols like Nostr to create tools that foster freedom, collaboration, and realness without the chains of big tech overlords.

Full summaries from both agents and transcripts are available here:

https://github.com/humansinstitute/everest-pipeliner/wiki/Two-AIs-Analyse-No-Solutions-to-extract-the-Philosophy-of-Sovereign-Engineering

Interesting to see how repeated calls back to agents can lead down a specific pre-programmed ideological path. I think I prefer models with ideologies close to my own, but the alternative is a good echo bubble popper 😉

My guess here is this is more driven by the system prompt / safety layer than the training.

No Solutions 5mo ago 💬 2

🤯

nostr:nevent1qqs8es49vsn4lgsah7k0m0w0qwfgwz78r3rzs0k74q7zle47cf2temqpzdmhxue69uhhwmm59e6hg7r09ehkuef0qgsfgg2lg25kxdwg0l9eazq6pwak9wd8j4geuyyu7hua9mmpw6qlvgsrqsqqqqqp4ma9pl