Avatar
Leo Wandersleb
46fcbe3065eaf1ae7811465924e48923363ff3f526bd6f73d7c184b16bd8ce4d
https://walletscrutiny.com https://nostr.info Working on Bitcoin, Nostr and being a good dad.

Your thoughts would still be your thoughts. I would want such a tool to make sense of the hive mind. If I through this thought at my followers, what might come back? Now that tool could be tuned to go wild or be more conservative and I might agree with some of it or not but it should be inspiring in many instances. And as for the writing help, I'd keep it to grammar and spelling. It would help me get more creative with words as I often feel insecure on how to use lesser used expressions and swap them for simpler language to not say something stupid. With such an assistant I could experiment more. It surely could also help with mention suggestions or timing posts but I would not want it to guess my own writing.

The sweet mustard is a sugar bomb but it belongs to Weißwürst so what should I do? ;)

Where could I best buy some EUR with my BTC? The last times I used Bisq but the fees are just ridiculous. As a taker I have to do **3** on-chain transactions and pay 0.7% trading fees.

And Bisq does not show clearly how high the on-chain fees are. Turns out Bisq as of now pays the equivalent of $30 per TX! Yeah, great! Guess I'll not use Bisq until I feel like trading full Bitcoins or something.

That local LLM could be open source and even link you to posts of Alice and Bob to back its claims. Of course this would be predictive for other human beings and thus no real replacement for the real interaction but it's not about accepting these as real. It's more about "What would Alice do?" thought experimentation.

We imagine social interactions before we act them out for the first time and an LLM can help with that I would say.

We are social beings and want to be heard. We interpret the world and share our interpretations to see what sticks. If it sticks, maybe there is something of value to that interpretation? And so conversations are 99% repeated and recycled arguments but we still want to share and hear them as we are not a hive mind that would know what sticks and what not a priori. And to make things even worse, over time, things stick differently. The Overtone window slides. We have to update all these billions of brains one brain and one interpretation/meme at a time.

We would probably not need AI but only state of the art LLMs to get these feedback loops "offline". Imagine a local LLM that's trained with all of your follows conversations. It could anticipate individual reactions and even argue about them. Alice probably will give you a 🤝 and Bob might zap you. Carol will not react as she never chimes in on this topic.

I find this thought kind of creepy. Imagine writing something thoughtful, getting your feedback from the LLM and not sending it, being satisfied with or scared by the "fake" feedback.

I would still want such an assistant that runs locally and checks for grammar and style, too, cause why not? I think the result would be more engaging posts and if it was integrated in clients it could make for more engaging posts on a broad scale making a dent in nostr's adoption as a whole.

Sadly this is also something a psychopath would say to get gullible people to buy his bags.

Everybody has to miss the train a dozen times before they jump on board for mostly greed but greed is just a Trojan horse to get them to dig deeper. If they don't dig deeper and sell it all for fiat - add it to the list of trains missed.

Everybody will buy sats eventually.

Nobody likes conscription and as a libertarian I see it as some sort of slavery, too but that is what countries do in war time. And judges weigh personal rights against collective rights and give it a go.

Also what are non-private transactions? Does that only mean transactions with the state or also B2B?

Fees are a joke. If you buy a house with Bitcoin, you pay what? $7 in fees? That's a tiny fraction of a percent in fees.

Did he not drop financial regulations? You can now use foreign currency as you please - and bitcoin for that matter.

Feature Request: Disregard likes and replies from people that are not followed by any of my follows by default. These engagements should only be shown when I switch them on or after clicking a "show more" button.

Nostr is much more open than xitter yet on xitter 50% of my notifications come from accounts with zero follows and zero followers mentioning me to spam some airdrops. Nostr will be many times worse if we don't find good heuristics and this follow-of-a-follow to me appears like a very natural heuristic.

Ok, anybody reading those notes of you where you used non-english words would have come to the same conclusion and as a programmer I would have thrown an English dictionary at your notes and highlighted all non-English words. No LLM needed but the fact this requires no special tool or programming is miraculous. I guess, LLMs are already a great forensics tool.

There is people that think that all the surveillance will achieve nothing as ti's too much data to read through. Yeah, well ...

Well, many of the current users will notice and many if not most will have their keys backed up and make noise if Damus did that.

Or the mother. Or both. WTF? Somebody is really sick here, staged or not.