Been using @DevinAI to do autoresearch on Kev overnight with @Modal Outposts (this gives Devin’s Cloud agent full access to GPUs) as well as Devin’s macOS VMs to do some work on MLX. The workflow has been super powerful. I also set up a bunch of Devin Automations for a lot of routine repo maintenance work. Definitely some room for improvement though. Need to probably tweak some automations to score PRs and Issues before just blindly taking action and trying to repro etc. same thing for Devin AutoReview. Fwiw I don’t think these headwinds are unique to us, OSS just has different security and trust model for agents vs. internal work.