progress. every repo starts with a (null) then evolves into a class determined by what kind of work youre doing. xp gain determined by harness runtime, commits, and code language being written.
D retweeted
Don't use this
Build your own software using their tokens
So when their tokens become too expensive
You can switch to your own GPUs
Your compute. That you control
So you yourself can't be controlled
You need to control your stack -- or you become enslaved
after tinkering with agents for months the conclusion I’ve landed on is that they will be irrelevant soon
Yap method is undefeated
One pattern I find useful for working with LLMs is a nice long ramble session. Sometimes the LLM needs more bits to understand what you're trying to achieve, but you're too lazy to type them. In these cases I like to lean back, switch to /voice and just ramble for like 10 minutes, total mess, anything goes, full stream of consciousness. Sometimes I declare it up top, something like "switching to speech recognition sorry for any typos...". Sometimes I turn it into a small interview of a few turns. But I find that the LLMs are somehow very good at reconstructing long incoherent rambles and often their echo of your own tangle of thoughts comes out quite a bit cleaner than what you started with. The result is that you improve the mind meld and have to correct things less from that point on.
nbd everything’s fine 🙂
letting 5.6-Sol audit my entire agent stack top to bottom across 6 different machines. 4 days in now and the amount of optimizations it has identified is wild.
