Code sorcerer by day, crazy sport fan by night.
linux-powered, open-source lover, and always one git push away from magic. Unless a match is happening.
I've been allowing the swarm to operate for a full day now. It's gotten a lot done. But I've intentionally allowed the agents to continue compacting their contexts, over and over.
The results are interesting. First, they've started to lose their particular identities. The coders is doing crap analysis. The refactorer finds it has nothing to do because the coder did it. The refactorer has decided that sending message to other agents requires my permission (it doesn't). The coder simply forgets to hand off to the refactorer until I remind it. The architect decided to not run mutation tests because they take a long time.
Fascinating.
Given all that, and the constant babysitting that is required, it has gotten a LOT done.
As the number of testing scenarios has increased, the testing procedures have gotten quite slow. The continual retesting is very inefficient. I'm going to have to implement impact analysis to drive the tests so that only the things that have changed are tested.
@steipete@levelsio Depending on your plan at claude.ia u have limited tokens per session of 4 hours or even within a week. That message means exactly that, you run off tokens. Pete talks and thinks without that limit and that is ok if you have money enough to pay as you go on your LLM subscriptions
@MatthewCoast that sound really old dude... in many countries in the UE things are quite different. Maybe thats is the reason we go so slow in everything and we are having less kids than ever, and the reason is man are also taking care of kids / house / bills / job / mental health.
I keep asking… how does Real Madrid always do it, even when the whole world is watching?
After Benfica vs Madrid, the headlines are:
Prestiani = racist.
Vini = fighting for justice.
Mourinho = controversial comments.
Why is that the only narrative?
Nobody’s talking about Valverde’s incident.
Not even the cards Madrid escaped.
Why is the spotlight always selective? 🤔
And if UEFA is investigating the alleged racist incident, what about the officiating?
Is that not worth reviewing too?
From my TikTok - non-technical family friends have asked me to explain Clawdbot/OpenClaw/Moltbot and agents in the context of what they use, which is ChatGPT