[int_19h]

My record for a single uninterrupted session (albeit with Codex, not Claude) is 80+ hours. It was very productive, too.

The trick is having large, extensive test suites and forcing the agent to run them regularly.

[danmaz74]

So I guess that a lot of those 80 hours were spent running the test suite between changes?

[int_19h]

Yep. I should add that the current crop of models is much more tolerant of something like this, compared to where we were a year ago - as in, they are quite willing to wait for a long time for the test or profiling run to finish without giving up on it, if the instructions make it clear that this is normal and expected.

[danmaz74]

I think that waiting or not is mostly up to the harness, not the model itself.

[nujabe]

An agent can’t have an “uninterrupted session” if you have to be “forcing” it do stuff.

[int_19h]

"Forcing" here basically means giving initial instructions that clearly require passing the tests as a condition of finishing the work. The agent still works uninterrupted.