[rosenlykke]

Fair point. I don't see it consistently myself, but there are def moments where it just stops parsing context on simple tasks/stops thinking. Not sure if it's model regression, context rot, or just prompts getting routed to a different/wrong expert in the MoE for a stretch — dunno.

[tstrimple]

I've got an example that isn't just coding. I've used CC as a book recommendation engine for a few months now. Initially I had really good results. We built a SQLite database of my reading history from audible and kindle libraries and tuned it based off of my "reviews". Since Opus 4.7 it suddenly lost the ability to check the SQLite database for things I've already read before offering recommendations. The last time I interacted with it, I told it I had completed Book 2 of a series and it recommended Book 1 of the series to me. I had never previously seen Opus be so stupid with all the information available to it. Nothing changed in my configuration between when this was a useful tool and complete garbage other than the model and harness upgrades Anthropic pushed.