This is an idea that my dad and I, who have set up dueling OpenClaw agents, have been tossing around a lot lately. It's been so much fun messing around with OpenClaw, but at the end of the day I'm writing this post because I don't have anything better to do with all of that excitement.
> These are not hypothetical questions anymore. They're engineering problems.
> Not the human kind. The infrastructure kind
> Not better models. Not smarter agents. Sandboxed accounts. Scoped permissions.
2 comments
[ 3.2 ms ] story [ 11.3 ms ] thread