Finally just set up voice dictation

Now setting a prompt to explain to the transcriber that I'm not working with a "Chimney" protocol for moving "Cashew" around



It's Whisper, locally. Also the first time I'm doing anything useful with local AI

Just a moment ago on Twitter, Saifefean Ammous (The Bitcoin Standard) referred to "Keynes' moronic writings"

I'm sure he'll agree it's only fair, given his choice of words, to point out that Ammous's writing are worse. I tried to read his slop, but he made the classic error of thinking that inflation brought Hitler to power and therefore I had to put his book down after reading just 20% of it

https://xcancel.com/saifedean/status/2095088845230354884

Unfollowed two npubs just now because they turned out to the generic big-blocker bots that we see so much during attacks on Bitcoin

Why do so many attackers (including BIP110ers) always run out of ideas and just randomly attack Lightning and use emotional MoE arguments?

Makes me more convinced that Lightning is the correct approach 🤣, and that we have the right incentives and game theory for Bitcoin

We're making an asset that nobody wants to spend, and which can be transferred with private instant settlement. This is how you play the long game, making it the world's MoE

Maybe instead of making big PRs, especially to projects that we haven't contributed to before, we should create a high quality Issue

This issue could include the problem and also the solution, especially a high quality description of how to solve it. If the submitter (and their agent) has already implemented the solution with tests, I think I'd find the agent's writeup of the solution to be more useful then the solution (alone).

If I was a maintainer, I think I'd find the Issue much more useful than a PR. It would be easier to review and implement - with AI help.

With a PR, there is always a fear of some error or security issue being introduced, accidentally or otherwise.

#TL/DR Show me the prompt, not the code

My language teaching bot is so good, that I'm even enjoying learning this table:

I'm having a lot of fun using and writing my new language bot.

First time in ages that I find it fun to study languages, and I really think the bot is good at remembering my preferences.

It's the first time I've ever implemented - or really though about - how to manage context. As well as the obvious stuff - like compaction - my bot also has some memory-like systems that are for language-learning specifically. For example, it keeps track of mistakes and successes in grammar topics; all labelled and categorized by the llm.

This allows it to keep a compact summary of the mistakes I'm making in vocab and grammar and so on.

And also a 'learner profile' where the llm keeps a summary of my preferences and basic life facts. For example it has learned that "Bitcoin" is one of my interests

I'm not a language teacher, so I'm making sure that I design the system such that I don't have to make a decision that might be a bad decision; everything is llm-guided

It's just for me and one friend, not planning to share