alt Hacker News> where previous models interpreted instructions loosely or skipped parts entirely, Opus 4.7 takes the instructions literally. Users should re-tune their prompts and harnesses accordingly.
interesting
Replies
This made me LOL. They keep trying to fleece us by nerfing functionality and then adding it back next release. It’s an abusive relationship at this point.
coming more in line with codex - claude previously would often ignore explicit instructions that codex would follow. interested to see how this feels in practice
I think this line around "context tuning" is super interesting - I see a future where, for every model release, devs go and update their CLAUDE.md / skills to adapt to new model behavior.
This sounds good, I look forward to experimenting with it.
I like this in theory. I just hope it doesn't require you to be be as literal as if talking to a genie.
But if it'll actually stick to the hard rules in the CLAUDE.md files, and if I don't have to add "DON'T DO ANYTHING, JUST ANSWER THE QUESTION" at the end of my prompt, I'll be glad.