So the real benefit is succinctness and readability... would be nice to have a comparison against other scripting languages or plain text, to prove better performance or accuracy.
I would say you're right in that with succinctness comes constraint. And the constraint is really the point, not the brevity. It's small because it can't do arbitrary things, which is exactly what lets you read one and approve it (and for hopefully anyone to understand), and what makes it run the same way every time.
A comparison would be useful. No published benchmark yet, but that's fair to ask for, and probably the next thing worth putting out.
Would be interesting if you could post more details about what you captured.
Claude code seems to have a pretty robust harness and memory. It's a time saver to not include project context in our prompt, since Claude manages claude.md but I haven't used OpenCode to compare.
I agree that's the status quo right now. AI does ~80%-90% of the job well but in many cases, users require 99%+ reliability and the work still requires a human. The real scare is that the projection of AI intelligence will reach ASI and then that gap will close or be marginally insignificant.
The vision of independent AI systems will eventually come to fruition, just not today. Not yet.
We need an agentic platform that has sandboxing built-in well. Giving agents a disposable VM is nice but I'm already hitting my Mac mini's space limit.
Claude Cowork does this on Mac and ears several gigabytes of on disk storage, drives me crazy, because it does this if you click on it without ever using it.
