"On the internet, nobody knows you're South African"

😆 love that - but so true.. as SAffers we limit our marketing to Africa but really the whole world can be your customer! This is a huge arbitrage opportunity.

## Why I am sidelining DVMs for now

When I started to grow tired of random posts on nostr I had a plan to create a DVM to tackle the problem of noise. I wanted a feed that caters to people like me in it for the professional discussions and meaningful FOSS work.

I used the LLM approach because simple hashtag parsing can only do so much. First I thought I would fine-tune a BERT-like model that should be easier to self-host. It turned out to be a harder goal to achieve than I expected.

I wanted to use GPT4-o to help me generate data for the fine-tuning. Sadly that was a bummer. It screwed me over so many times with garbage, I got exhausted.

Then I downloaded a bunch of high-rated stackexchange posts to be clustered and used for the fine-tuning.

This already took me more time than I wanted and realized that for a PoC I might as well use openai api. So did that and started experimenting with different prompts for GPT4-o mini.

In the meantime I got acquainted with the python based nostr-dvm framework and setup the basics I need for a DVM service.

After some grind I got everything working but still was not very pleased with the classification results.

Now, I know I could have put in even more time to really nail that prompt but I kinda lost my faith and appetite. I successfully use AI to learn and generate rudimentary code and chat about ideas. But what I needed is to generate a feed without manual intervention. AI people tend to recommend techniques to improve results that are borderline witchcraft. And every single time GPT finds a way to hallucinate plenty of stuff that I did not expect, no matter how hard I seem to try. This is my experience from months of daily interaction with GPT4-o too, which is much better than the mini version.

So no, I won't get trapped in the ai hype again. It is what it is: without human oversight these things are still worthless. I'm not aiming for a 90% usable thing, and I don't have a straightforward way to get to a 100%. No one has because these stochastic models are not AIs at all. They are mimicking parrots, nothing more. And this direction is a dead-end if you ask me.

🚀 Help Us Print Hope With Bitcoin T-Shirts!

We want to print 10 T-shirts to represent Hope With Bitcoin during our humanitarian actions and raise awareness of Bitcoin’s impact.

🎽 Cost per t-shirt: 8,050 sats

🎯 Goal: 80,500 sats

Your support will help us spread the message and make a difference!

now imagine how much more you do not know about your phone and how it is spying on you... you get vpn and the app is leaking your location.. lol

for this reason you should have at least one with the grapheneos on pixel 6 or higher

higher (6 and 7 will be supported until 2027) where you practise privacy hygine, protect yourself and your family by making right consumer choices! you can also put this system on some tablet devices

you can get a second hand device and flash it with the os or buy one already preinstalled.

Come to our meetups to learn how to do it or request an order and we will provide such a device to you with a clean and fresh graphenos.

“They can cut all the flowers, but they can’t stop the spring…” — Pablo Neruda #quotestr #bloomstr #bitcoin 💐