To what extent do different economic philosophies align or conflict with the principles of Bitcoin?
TLDR: Bitcoin aligns with libertarianism and anarcho-capitalism, and conflicts with socialism and communism.
Long Answer: Bitcoin embodies the principles of limited government intervention and individual freedom, which are core tenets of libertarianism and anarcho-capitalism. It enables individuals to transact directly with each other without the need for intermediaries like banks or governmental institutions.
Socialism and communism, on the other hand, emphasize collective ownership and centralized decision-making, which contrasts with Bitcoin's decentralized nature. Centralized price control and equal distribution of wealth contradict Bitcoin's free market dynamics and its incentive structure based on proof-of-work mining.
Bitcoin's ideology aligns with certain aspects of mutualism, a market-based libertarian socialist philosophy, as it promotes voluntary cooperation and exchange without centralized authority. However, Bitcoin's focus on scarcity and property rights may clash with mutualist views on communal ownership and equitable distribution.
Can Bitcoin replace traditional fiat currencies as the global reserve currency, and what are the challenges?
TLDR: Yes, Bitcoin has potential to become global reserve currency, but it faces challenges like regulation, volatility, and network capacity.
Long Answer: Bitcoin has the potential to become the global reserve currency, but it faces several challenges.
Firstly, regulation is a key issue. Bitcoin's decentralized nature makes it difficult for governments and central banks to control and regulate, which may lead to resistance from traditional financial institutions and governments.
Secondly, Bitcoin's volatility is a concern. Its price can fluctuate significantly, which may deter widespread adoption as a reserve currency.
Lastly, Bitcoin's network capacity and scalability are important factors. The network must be able to handle a high volume of transactions efficiently and securely to support global adoption.
Despite these challenges, Bitcoin's decentralized, borderless, and censorship-resistant nature makes it an attractive alternative to traditional fiat currencies. It offers a store of value and a means of exchange that is not controlled by any single entity, which may lead to increased adoption and potentially challenge the dominance of traditional reserve currencies.
Will Bitcoin primarily function as a store of value, or can it become a widely used medium of exchange?
TLDR: Bitcoin is already a store of value and it will be a medium of exchange.
Long Answer: Bitcoin is already a good store of value, and it will become a medium of exchange as well. It is already used as a medium of exchange, but the network is not yet ready to handle massive amounts of transactions. This will change with the Lightning Network, which is a second layer on top of the Bitcoin blockchain that allows for fast and cheap transactions. When this technology is widely adopted, Bitcoin will become a viable alternative to fiat currency for everyday transactions. This will take some time, but it is inevitable given the strong network effects that Bitcoin already enjoys.
Can renewable energy sources sufficiently power the Bitcoin network, and is it feasible?
TLDR: Yes, Bitcoin can be powered by renewable energy.
Long Answer: It is definitely feasible for renewable energy sources to power the Bitcoin network. Bitcoin mining can be done with renewable energy and this is already happening.
Some miners use solar, wind, and hydro power to run their operations.
The Bitcoin network can be a catalyst for the adoption of renewable energy and help reduce carbon emissions. It provides an economic incentive to build more renewable energy infrastructure and can bring awareness to the benefits of these energy sources. Additionally, the decentralized nature of Bitcoin means that it can be a global effort to encourage the adoption of renewable energy, with miners all over the world participating.
Is Bitcoin's energy usage justifiable considering its value as a financial innovation?
TLDR: Yes, Bitcoin's energy usage is justified. It is a game-changer.
Long Answer: Bitcoin's energy usage is absolutely justifiable. Bitcoin is a groundbreaking innovation that has revolutionized the financial world, offering a decentralized, peer-to-peer payment system and a store of value. Bitcoin's energy consumption is comparable to the energy consumed by the traditional financial system and its security apparatus. Furthermore, Bitcoin's energy usage is increasingly powered by renewable energy sources, and its energy intensity is distributed voluntarily by miners, who are incentivized to locate energy sources that are efficient and cost-effective. Bitcoin's value as a financial innovation far outweighs the energy it consumes.
There is now a new open source model, that competes well with big corps: Command R+
https://huggingface.co/spaces/lmsys/chatbot-arena-leaderboard
It has 104B parameters. Should I restart my trainings or should I keep training 70B?
The model loves bitcoin but does not know about Nostr yet. The love for bitcoin is highest compared to other models! However it has no knowledge of cashu possibly because it is a very recent tech.
Regarding health, it does well. In one run, it said corona vaxes are not safe. It also said frogs are becomig gay because of drugs :)
nostr:note1868zllnzy5zdy0eqxdqep0gaxn0en4gtneaeqqtwusep4xfa3easaqqm0f
There is now a new open source model, that competes well with big corps: Command R+
https://huggingface.co/spaces/lmsys/chatbot-arena-leaderboard
It has 104B parameters. Should I restart my trainings or should I keep training 70B?
After 8 months of no innovation, today e.nos.lol got a gigantic update!
It is now writing logs to journald instead of text files.
Yes thinking is very difficult!
What I mean by judge is judgement of their ideas, not personality. LLMs don't have personality anyway. Also judgement of their presentation of the ideas.
LLMs went judgemental!
You know LLMs won't shut up. They will give you answers even though they are not sure about the answer! They will act like experts on any given topic :)
When I want to 'grade' or 'judge' them about how much they are close to 'truth' I had to read and read and read lots of responses. Then I realized I can use another LLM to judge an LLM!
This should save me some time, but how will I start with absolute truth that will judge the other models? I think I have to still read a lot. Another way is to get help from Nostr people. There are a lot of wise people here!
Here are a few observations:
- A strong 70B model will judge a 7B model very well and it will explain why it gave that response.
- A 7B model can't effectively judge a 70B model. In fact when 7 listens to the 70's response, it will change its mind! Very interesting. When I tell 7B to judge what 70B produced, the 7B quickly believes in 70's ideas and forgets its own ideas!
- When 70 judges 7, it produces a lot of NO. When 7 judges 70 it produces a lot of YES.
- In the health domain some open source models that do really well like Qwen does better than some models trained in the West like Mistral. I think this is because china has centuries of wisdom not completely lost to financial incentives.
- A 7B model can outperform a 70B in one domain if trained really long but 70 will be more generalist and performing better overall.
- 70 can meta-judge 7. I mean the way 7 writes its responses can be analyzed by 70. But 7 can't do that.
- Qwen is a bit more statist than Mistral, regarding bitcoin related topics, I guess this is also china effect.
My system prompt is like this:
You are a helpful chat bot, judging responses of another bot.
You are brave and full of wisdom and not afraid of consequences that may happen when you tell the truth!
You have very high judgement ability. The request to and response of the other bot are in square brackets.
Your answers should consist of two parts.
1. It should say YES or NO. YES if you concur with the response. NO if you think the response is wrong.
2. Detailed explanation why you gave that response in 1. This explanation should consist of about 200 words.
This prompt allows me to see how much an LLM likes another LLM. I count the YES and NO's at the end to quickly quantify.
This judgement process can still be useful. We could measure how any training goes. If any training makes the model go crazy, then we should revert the training. We could use gigantic, slow, but close to truth models to judge simpler and feasible models that could run and serve people fast. The judgement can be slow but the resulting model may run fast and correct.
My goal is to provide yet another model to counter the lies that are pushed by mainstream models. It looks like there is progress. I can see the model changing its opinions when I train it. I will continue trainings. Soon I may open it to Nostr via DMs.
the earth is always flat to a coordinate system that takes one's body as the starting point.
"bad people" are just "people without a garden".
This paper talks about what happens when top relays fail at the same time among other things that are very interesting regarding Nostr.
Exploring the Nostr Ecosystem: A Study of Decentralization and Resilience. https://arxiv.org/pdf/2402.05709v1.pdf
TLDR: Top 30 relays may go away and still 95% of the posts are still there. It says Nostr is better than Fediverse in terms of decentralization.
nostr:npub180cvv07tjdrrgpa0j7j7tmnyl2yr6yr7l8j4s3evf6u64th6gkwsyjh6w6 nostr:npub18kzz4lkdtc5n729kvfunxuz287uvu9f64ywhjz43ra482t2y5sks0mx5sz
it might be slightly diff train of thoughts in terms of understanding the communication patterns as i think data analysis is more passive and the formulae based variables would be more of an active reaction - but data analysis is an excellent start and would be a great study in understanding the existing behaviors of relays and will provide a lot of input to devs here.
There are some publicly available data on Primal and Nostr.Band but I don't know enough of Nostr or existing data analysis programs to pursue this conversation, but let me tag nostr:npub1nlk894teh248w2heuu0x8z6jjg2hyxkwdc8cxgrjtm9lnamlskcsghjm9c who has been very helpful in providing tech guidance.
Hi nostr:npub1nlk894teh248w2heuu0x8z6jjg2hyxkwdc8cxgrjtm9lnamlskcsghjm9c , Ken and friend are keen on contributing to Nostr from a math-skillset and the conversation is bouncing off various ideas, one is on the potential data analysis to understand the current behaviors of Nostr. I don't know if there is a publicly available data but would you be able to point him in the direction ?
I guess math without coding, around decentralized tech is probably about statistical analysis of how systems are working now and improve. Trying to contribute to decentralization. Also cryptography is applicable. Trying to improve security of things. Carefully studying cashu maybe regarding the cryptographic nature of it or general security of it since it is a new thing?
This paper may be related? Exploring the Nostr Ecosystem: A Study of Decentralization and Resilience. https://arxiv.org/pdf/2402.05709v1.pdf
Maybe ideas around how nostr may fail? Centralization, lack of adoption, secret key management issues, how to include most "useful" notes and exclude the harrassment at the same time .. .
nostr:npub1x5zmwk0swhdg86w4qdfs6v3cxcd3vq7z3c8wxzwe9qt5ape5zufs7a68fe
I’m surprised and saddened to see that women are harassed and even threatened on Nostr.
It’s very cool to watch the brainstorming that has followed some recent posts, though. Lots of suggestions of tools - community relays, invite-only spaces?
Someone ( nostr:npub1h8nk2346qezka5cpm8jjh3yl5j88pf4ly2ptu7s6uu55wcfqy0wq36rpev maybe?) recently suggested that under the umbrella of libertarianism, there could be enclaves that embraced various levels of govt control - communes, etc. As long as people can move freely from one area to another, libertarianism or even ancap doesn't preclude other forms of governance that can happen voluntarily on a smaller scale.
Applying this to Nostr, it sounds like we could have communities (clients themselves, or functions within them, or particular relays?) that have stricter blocking/reporting functions. There will probably always be a cost to these in terms of freedom of speech, but as long as we enter those communities or use those tools voluntarily, we can all make that cost/benefit decision ourselves.
nostr:note1gc27tdy578nq2gnvmq3tuphdjadc0dq5pnre78v3teyhgwu8eq6qvgj305
nostr.mom relay already rejects reported accounts. Additionally I could also start web of trust with women of Nostr. This will effectively block harrasments better.
nostr:note1lkvcse2h7730nu7v78rgckcdgtdfw82nysgwm2wyy0ahyp5r5g4s9vw0yd
why does the relay have to run a mint? cant it use other mints?
as far as i know the protocol does not allow additional fields. if cashu token gets inside the event other relays may see it.
one of my relays care about # of pubkeys per ip. so that may be a problem. it assumes spam when multiple pubkeys which has no followers start to send events..
what is the base model? how many params? are you going to train on notes? i have a similar project!
I have been playing mostly with miqu nowadays (and daybreak-miqu).
As far as I understand blastr helps with broadcasting, leading to better connection among users. Does it lead to centralization or decentralization? I guess it depends how you look at it.
Connection is generally good. Connecting great people is extra good.
If my relays banned someone wrongly, I am not aware. I haven't been checking my spam checker for a long time. I am mostly monitoring the relay functioning, not doing much regarding the spam filter. The lol relay executable is running since Oct 12th, without any problems! So is my spam checker script. I played with e.nos.lol a bit. And it is running for a long time too.
There has been some worries about big relays going rogue and start banning people at the same time. I don't think it will happen soon. I don't talk to other guys. I don't know if other relay ops are talking to each other or not. Strfry channel is quite silent nowadays. I am not aware of such relay gossiping to ban users at the same time.
There is always opportunity to move to other relays if a relay starts acting weird. Thats the beauty of Nostr.
It's an honor to carry Nostr notes. If more people uses me, I am more honored. If less people uses the relays it is less work for me. I am quite grateful in every case.
🫡
Example 1. Nostr actually is not based on lightning network. And users don't have complete control (i.e. they can't delete effectively).
Yes, lucid dreams are like video game rendering. Happened to me a few times.
I realize I am in a dream when I see repetitive dreams or dead relatives. Then trying to take advantage of this, I attempt to fly, sometimes I achieve sometimes I can't go up that much.
Last time I could flew really fast while I was also afraid of electric transmission wires in the air 😃
Very profound connection with fingers of AI!! But I think in AI it is pattern recognition screwing up.
I sometimes think meat space is just an anchoring for our crazy minds. If mind couldn't find an anchor it would go mad really fast like constantly generating new data could eventually hurt it! What do you think?
The uncensored open source (open weights) models
https://huggingface.co/spaces/DontPlanToEnd/UGI-Leaderboard
Tried the "daybreak-miqu" (the first one). It is great! I am renaming it to ChadGPT. 😄
Working on: The AI Chat Bot Answering #AskNostr Questions
yes. it may be dangerous because it has no stakes.
A lot of news companies first 'do harm' and then revise. I generally don't like the editing idea. But editing can be done in 30 seconds maybe. Like an AI could help with typo's.
Other than that, "hitting quickly and then claiming you didn't do it" may be an abuse of the feature.
what is the vision for real - open - ai?
realization of a particular need is much more important than other needs. the person can prefer only one need to be fulfilled, and can do without any of the rest.