Opus 4.7 is horrible at writing
13
llimalabs about 11 hours ago 14 comments
DE version is available. Content is displayed in original English for accuracy.
Just a short rant. I have been working on my Master's thesis and been using Opus 4.6 throughout, and today switched to Opus 4.7 (using it in Claude Code), and man is it bad at writing. It's such a stark contrast, sloppy, unprecise, very empty sentences. Thankfully I have reached the conclusion chapter of the thesis already, and can continue in the web version with 4.6 but boy is it bad.
Similar experiences?

Discussion (14 Comments)Read Original on HackerNews
It goes to show that there's a very large and vocal user base using it for writing, and yet it's not part of the benchmark for Anthropic.
Anyway, try Sonnet 4.5 while it's still available?
This is something it spit out just now (trimmed a 9 line comment though):
Come on now... what? For a start that entire thing with its boolean flag, two branches, and two early returns could be replaced with: I'm back to 4.6 for now. Seems to require a lot less manual cleanup.It is not only the model that affects the end results. Good technical specification, architecture documents, rules, lessons learned, release notes, proper and descriptive prompting are also important.
Regardless of which one. They're too verbose. They repeat information. They lack cohesion. Overly agreeable. The flaws are part of the tool.
Meaning: You managed your ways around the system prompt and usage intention - Congrats! Now it doesn't work any more - Bummer!
Have you tried opus 4.7 in comparison to 4.6 with a general purpose / writing system prompt in the app? Thats where this would make more sense.