Avatar
ElectronicMonkey
45c41f21e1cf715fa6d9ca20b8e002a574db7bb49e96ee89834c66dac5446b7a
Author of nostr blogging client: https://flycat.club/

欢迎试用新版客户端👏

jb55 一直在探索我早先对nostr感到最激动的可能性。我觉得这是nostr上最被低估的特性,也是我后面想花最多精力探索的一个地方(可惜我现在被一堆flycat 体验上的活拖着)这个想法是把代码直接存到 relay 上,代码的作者可验证(有哈希有签名,解决分发代码的信任问题)、note的数据格式统一,只要客户端再配合上相同的runtime,就可以运行代码了。看着好像是非常简单的一个idea,但这不比 EVM 智能合约 web3 之流强上一百倍?我们要想想所谓的 web3、smart contract 到底要解决什么问题?就大部分场景(尤其是 web3/社交等等),一个nostr这样的信任保证和relay机制才是正确的选择。而不是p2p/blockchain。 jb55 has been exploring the potential that initially excited me the most about Nostr. I believe it is the most underestimated feature of Nostr and the area where I want to dedicate the most effort in my exploration going forward (unfortunately, I'm currently being occupied with a bunch of activities related to Flycat experiences). The idea is to directly store code on Relay, with the code author being verifiable (using hashes and signatures to address code distribution trust issues), and the note data format being standardized. As long as the client is equipped with the same runtime, the code can be executed. This idea seems to be a very simple one, but isn't it a hundred times more powerful than concepts like EVM, smart contracts, and web3? We need to carefully consider what problems web3 and smart contracts are truly meant to solve. In most scenarios, especially web3/social contexts, a trust guarantee and relay mechanism like Nostr is the right choice, rather than relying on p2p/blockchain.

glad you find my client! I plan to store it online and also add a export/import JSON file option. I want people have fallback option when they can't fetch it from relay in the first place

In the first couple month I was thinking question like how to solve problem about data losing on relay. After a period of time, some relays might just drop your data and you can’t find some of yours notes then.

Now I have different view. This is not a bug to solve, it is the perfect mimic of the interaction from human society. You don’t write down all the bullshit came from your mouth, we just talk and words goes into air and then some people forget about it some people remember you it but eventually they forget.

Public Relay is like this thin air that helps you talk with people just right at the moment. Like a coffee shop or a bar.

In the future,

The new president of our country will be : AI

the government staff will be: AI again

The currency will be: bitcoin, of course

And finally, The law will be written on blockchain

前几天我还在担忧 AI 如果被利用拿去做审查怎么办,删帖封号力量太强了。而国外的 dev 是在想如果能拿 AI 来做社区管理员对抗垃圾内容会怎么样。我想这大概就是出身决定思维吧😅

nostr:note1tc37f69gtc5d0zfch3mpqmhvnmet6cgux7668fpefzwah3t87h3sdgllp4

Replying to Avatar Stuart Bowman

AI Powered Mod Tools for Nostr Communities on Satellite

Hey everyone, I want to tell you about something I've been working on — I wasn't planning to post about this today because it's not ready quite yet, but I noticed that nostr:npub1l2vyh47mk2p0qlsku7hg0vn29faehy9hy34ygaclpn66ukqp3afqutajft had created a new nostr community n/AI this morning — and it just fits too perfectly.

So here goes: I'm working on a feature that will allow community founders to "spawn" an AI moderator to help detect and defend against spam, organize their community, and eventually do a bunch of other things.

I believe this capability may become an essential tool for nostr to survive the coming onslaught of AI-powered spam. It seems to me that if we really want to have a realistic chance of maintaining public, human-led social spaces, we have to match AI with AI. It's not something we can afford to leave on the table.

On a technical level, nostr is a perfect fit. The shared, permissionless, data architecture means that each community's AI can "live" on Satellite's server (or any server, actually) and, after having been nominated as a moderator, proactively sign events with its own pubkey just like a human.

The AI will be given a simple task: *Enforce this community's rules as written*.

So the human admin of the community can essentially set policy to be implemented by the AI. For example, if the AI decides to remove a post, it can be instructed to explain why it removed the post, and to specifically cite the "legal basis" for its action. Human admins will be free to tweak the rule, overrule the AI's decisions case-by-case, or remove the AI from its position of authority.

It's very interesting to consider where this leads, and what other things an AI that "lives" in a community may be useful for. For now I'm focused on getting an MVP with this mod stuff deployed on Satellite asap. I'm genuinely curious about what it will take to make this work well in practice.

If you want to open your own thread on the AI/Nostr intersection, here's the link to the community https://satellite.earth/n/AI/npub1l2vyh47mk2p0qlsku7hg0vn29faehy9hy34ygaclpn66ukqp3afqutajft

I'll be writing a lot more about this.

super cool! lol couple days ago I just post this note nostr:note1nqujw8jnhrn47zskun9z3nnp72sknq6la50k4x0txccty7wpkjts9tlk42 I guess that's the solution now!

thank you, I really like the new look

thx for you feedback! that's a great advice. it is not stable yet so you might need to refresh page after switching relays. also try checkout the explore feed that might provide more different feed on different group of relays

long-form post rendering in the short-note timeline on flycat undefinedrabble I heard you are looking for something like this

we need more diversity relays. and a way to identify those relays that you are interested at. but the very first step is to let user switch relays easily. that's why I do the relay selector on the global level on flycat. just release today. would love some feedback.

日本を拠点とする推奨されるリレーはありますか?

is there any recommended japan based relay I can connect to?