Gemini is getting less useful with each update. I could edit a pdf with the 3-pro model before but 3.1-pro couldn't edit the given pdf nor it could generate one for me.
If you want to "edit" a PDF, then Claude Sonnet works well, although what it's going to do is regenerate it from scratch trying to retain overall formatting. It can even do this for scanned PDFs and foreign language ones that need translating.
If you just need to create PDFs, not edit them, then Gemini notebook (notebook.google) works well and has Google's usual very high free usage limits.
AFAIK in general you can't really edit PDFs since it's not a reflowable format - even with Adobe tools all that editing does is modify the text within a text box - not reflow the document to adjust to any change in size of the text box.
The only thing I miss in emacs is concurrency/multi-threading. Apart from that, it's a complete software for me. Anyone can build it to anyone's liking.
Emacs has primitive concurrency (see Chapter 40, Threads in the Elisp manual), and because it's a Lisp, having nice concurrency is just a matter of programming.
This is what we really need and others should focus on this, niche settings for AI implementations. We are already tired of seeing the same stuff come up again and again when using AI. This is the type of stuff that can make AI more enjoyable and useful
This, I totally agree with you having a call and letting them explain the changes. One of my coworker used claude to write and push PR's and the message was so cryptic, it's not really understandable. I got him on a call and let him explain the PR. He also actually couldn't really interpret the PR message. I warned him not do this again. Now he writes by hand. I think communication between humans should be written by only humans. AI is not really good at communication.
Agent-shell.el for the CLI experience that's integrated with emacs. You can send things from emacs to your Claude code prompt and it will include the file and line numbers.
There's also claude-code-ide.el that gives you more of a cursor like experience with autocomplete, simple chat, etc.
claude-code-ide runs the claude TUI inside a term inside emacs with a little bit of editor integration on top. It's closer to the standard CLI experience than agent-shell is.
reply