Tip: identify PRs with this problem by looking for discrepancies between the metadata (files/lines affected) for PRs via GitHub API and associated commits in the time window.
The 8% and 50% numbers are pretty concerning, but I’d add that was for the “computer use environment” which still seems to be an emerging use case. The coding environment is at a much more reassuring 0.0% (with extended thinking).
Edit: whoops, somehow missed the first half of your comment, yes you are explicitly talking about computer use
> Most (probably >99.9%) players can't do that at the first attempt
Eh, both myself and my partner did this. To be fair, we weren’t going in completely blind, and my partner hit a Legendary joker, but I think you might be slightly overstating the difficulty. I’m still impressed that Gemini did it.
After being acquired by ServiceNow in 2021 for $510M and being rebranded to ServiceNow Cloud Observability, Lightstep is now being sunsetted with minimal fanfare.
I've seen this exact UI style a dozen times now and it's always accompanied with tell-tale overly verbose, overly dramatic text.