Every time I've used Gemini models for anything besides code or agentic work they lean so far into the RLHF induced bold lettering and bullet point list barf that everything they output reads as if the model was talking _at_ me and not _with_ me. In my Openclaw experiment(s) and in the Gemini web UI, I've specifically added instructions to avoid this type of behavior, but it only seemed to obey those rules when I reminded the model of them.
For conversational contexts, I don't think the (in some cases significantly) better benchmark results compared to a model like Sonnet 4.6 can convince me to switch to Gemini 3.1. Has anyone else had a similar experience, or is this just a me issue?
My favorite part of Zed is the problems/errors view. It's great seeing everything in one place and being able to edit multiple files with context at the same time.
That feature + native Git support has fully replaced VSCode for me.
A music library organizer, as a replacement for my current workflow with Beets (https://beets.io/).
Beets takes almost 5 minutes per incremental update of ~1000 folders of tagged flacs with my current configuration, when all I really want it to do is:
- fetch album art if not present
- create folder structure readable by Subsonic server
- symlink relevant files
Very raw and unfinished, currently only implemented adding new albums. However, 5 minutes to <1 sec is a promising improvement.
For conversational contexts, I don't think the (in some cases significantly) better benchmark results compared to a model like Sonnet 4.6 can convince me to switch to Gemini 3.1. Has anyone else had a similar experience, or is this just a me issue?