Very nice! I wonder whether that could be used to get LLMs to annotate pdfs. Say an "agentic" CLI like Claude Code or Gemini-cli reviews a pdf and finds typos, could it use this to annotate the pdf like underlining them in red or something of that sort? That could be nice.
Noteworthily, although Gemini 3 Pro seems to have much benchmark scores than other models across the board (including compared to Claude), it's not the case for coding, where it appears to score essentially the same as the others. I wonder why that is.
So far, IMHO, Claude Code remains significantly better than Gemini CLI. We'll see whether that changes with Gemini 3.
Honestly, if you didn't struggle financially, it seems to me that you've had a pretty good time and that your perception that you're not accomplished enough in how you used your time is mostly a byproduct of our tendency to always be unsatisfied rather than stemming from your past few years having truly lacked purpose :-)