231–238 of 238 posts
Earlier quoted context omitted.
I think it depends on the tasks you use it for. Bootstrapping or translating projects between languages is amazing. New feature development? Questionable.
New feature development in web and mobile apps is absolutely 10% more productive with these tools, and anyone who says otherwise is coping. That's a large fraction of software development.
Earlier quoted context omitted.
The flat earther argument. “The research is wrong.”
Yes, the research is wrong. And in science, it's not taboo to call that out. It's outdated, doesn't differentiate between people trying to incorporate it in their current workflow and the people who apply themselves to entirely new ones. It doesn't represent me in any way and I am releasing features to my platform daily now, instead of weekly. So I can wholeheartedly disagree with its conclusion. The earth is either…
Earlier quoted context omitted.
Yes, the research is wrong. And in science, it's not taboo to call that out. It's outdated, doesn't differentiate between people trying to incorporate it in their current workflow and the people who apply themselves to entirely new ones. It doesn't represent me in any way and I am releasing features to my platform daily now, instead of weekly. So I can wholeheartedly disagree with its conclusion. The earth is either…
If it is so self-evident that the research is wrong, that means there should be some research that supports the opposite conclusion then? Maybe you can link it?
The reason we don’t see any other research is because it’s neigh impossible to study a moving field. Especially at this pace.
If you have any ideas on how to measure objectively while this landscape changes daily, please share them with us. Maybe a researcher will jump on this bandwagon and proof you right.
Earlier quoted context omitted.
If it is so self-evident that the research is wrong, that means there should be some research that supports the opposite conclusion then? Maybe you can link it?
No. The reason we don’t see any other research is because it’s neigh impossible to study a moving field. Especially at this pace. If you have any ideas on how to measure objectively while this landscape changes daily, please share them with us. Maybe a researcher will jump on this bandwagon and proof you right.
With stuff like this, might be that all the infra build-out is insufficient. Inference demand will go up like crazy.
It'd be nice if CC could figure out all the required permissions upfront and then let you queue the job to run overnight
Earlier quoted context omitted.
It'd be nice if CC could figure out all the required permissions upfront and then let you queue the job to run overnight
Except it cannot really do anything unattended
The key is streaming NDJSON output to track cost per iteration and detect completion markers. The human stays in control by editing CLAUDE.md between runs to steer the project.