Dan was just a stupid note I made and then seeded with some memes until people started renaming themselves Dan 🤣

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.

Public miners will never be able to compete with miners who actually use the heat for something productive

I think they're all dead within 10 years if they keep just setting up data centers and venting the heat

The psyop of feminism has been perfect for them, in many countries they have managed to make many men and women hate each other.

Divide and conquer.

When you start from a wrong premise you do not get a correct conclusion.

They have started from the premise that men and women are equal and we are not equal.

You cannot make access tests easier for women in the case of firefighters, police or army, because fire or bullets do not distinguish between men and women. That is not equality, in the same way that gender quotas are not equality, that is positive discrimination.

Why don't we do the same for jobs where mostly women work?

Women and men are not equal, we are different and complementary. We have to accept the nature of each one, women are better in some things and men in others. We have to have the same rights as people, but not to benefit and belittle the other gender, which is what is currently happening.

The only thing that is sought with the current feminism is to create artificial roles, masculinize women and feminize men. When you make a duck behave like a cat, the only thing that can happen are bad things, it is an imbalance, perverting mother nature.

Whoever is a parent knows that girls behave like girls and boys like boys, without you influencing them.

The ultimate goal is to weaken society to obey, maybe you are not ready to understand it but accept it, men go to war, not women.

- Feminism

- Wokism

- Climate change

- Covid

- War

- CBDC

Those are their weapons.

nostr:note1ctmvlf9tl2uehqwyu32rzpxjh2vzul6s93ewgfmhp8vmt5anxjwseksed5

What is the most delicious fruit? Pineapple right?

If you wanted to set up a relay, so that anyone in the world could write and read to it, without the operator being forced to remove events, where would you put it?

I just spent a little time reading some of my old notes/conversations from over a year ago. I highly recommend it.

I could feel the excitement and hope in every conversation. I could sense the pure joy of finding an outlet for my thoughts and the new feelings of “belonging”, that I had never felt on the internet before. Blowing up threads with new found friends, having a laugh, taking ourselves too seriously, and then not seriously enough.

Nostr is still that place, but as time has moved forward and Ive become used to something, I think I have taken for granted just how special the people and the protocol are.

Friends, it’s been a trip, and that’s the only thing I want out of life.

🤙🫂

Bitcoiners probably are the perfect people to bootstrap nostr, because they have already demonstrated they have an insanely high pain tolerance for bad UX.

We’re still early

I find it tedious to repost my own stuff, but most of my followers are 6+ hours behind me and my reposters.

I tried to "stand under" my fear of heights, but I just couldn’t get over it. I guess I just don't understand

I love the noshole

There is now a massive power outage on a regular basis in your area.

How do you live without memes?

#asknostr

Why do we tolerate neo-Malthusians constantly whinging about overpopulation?

Genuine question.

The solution to these peoples problems is suicide. They believe the world is overpopulated, ergo they should kill themselves and help solve the problem they believe they have identified.

On other platforms I can’t tell them to kill themselves or I’ll get booted despite the fact it’s literally the logical conclusion of their own argument.

Why shouldn’t we meme these pricks into an early grave rather than allow them to shift the Overton Window?

Why do we tolerate neo-Malthusians constantly whinging about overpopulation?

Genuine question.

The solution to these peoples problems is suicide. They believe the world is overpopulated, ergo they should kill themselves and help solve the problem they believe they have identified.

On other platforms I can’t tell them to kill themselves or I’ll get booted despite the fact it’s literally the logical conclusion of their own argument.

Why shouldn’t we meme these pricks into an early grave rather than allow them to shift the Overton Window?

I wonder why there are constant travel ads on media when the climate agenda is to stop us travelling. I think they’re prepping people so once they have legal framework in place they’ll spring next ‘event’. Terror attacks push ‘need’ for travel controls. People won’t want to stop travelling so along with financial Reset which has to happen and the travel stop, people will jump into a DigID / CBDC / credit score system to get their allowed movement back with access to their new money. 🤷‍♂️

I really want to follow more npubs, but I can't figure out how to do that without my relay and feed filling up with nutjobs, stalkers, and porn.

Fear of Following is real.