@addyosmani My take on dev loops is to let them run on a deterministing state graph. GitHub issues, combined with authoritative state become the prompt. Check out https://t.co/yLAKvPe7Fb - disclaimer: this is my own opinionated approach ;)
@mvanhorn I have been building an opinionated pi extension that is running dev loops on GitHub issues end to end. Lately optimized on DeepSeek v4 pro, but also tested on all other frontier models. Been shipping 100s of PRs with it already. Feedback welcome! https://t.co/yLAKvPe7Fb
It genuinely feels to me like GPT-5.2 and Opus 4.5 in November represent an inflection point - one of those moments where the models get incrementally better in a way that tips across an invisible capability line where suddenly a whole bunch of much harder coding problems open up
@KnapsackPro Thanks for rolling out the fix. I know your service is pretty stable normally. We just had a couple of runs where the test suite did not report the normal coverage (~3% less) but the runs were still green. That's not cool, so better to have fails then!
@CoverallsApp down for a while now, which is blocking our CI pipeline. Website mentions "This website is under heavy load (queue full)
We're sorry, too many people are accessing this website at the same time. We're working on this problem. Please try again later."