safehuss

This looks very cool - would be cool if could use our claude logins aswell as codex...

Works like a charm on brave browser filter lists - thanks!

As time goes on, I become more and more convinced of this also. Also fits in with how many of us already learn via feedback loops - just now it's an LLM instead of a human giving you that feedback.

Very much agree with you. My own experience with calculus specifically is that I would attempt a problem or example myself, then review the solutions and if I'm stuck, I would not understand a proof or solution unless I copy out every single line as the lecture/textbook and even add to it.

The act of slowing down to ensure every line makes sense to me is one of the most valuable things for my learning.

This is awesome! Worked on something similar albeit a different industry.

For the more challenging scrapes, would highly recommend using the Chrome Devtools MCP to be able to attach the network requests, being made by the browser to the site, as context for your agent/LLM chat - this approach really helped me to write a solid API-based scraper (also using curl_cffi) and bypassed the old tedious playwright-based approach I used to rely on.

If the goal is to write emails purely using AI, then it is trivial to attach the MJML documentation as context to your LLM using context7 MCP or something of the sort. It's not a very complex language and its documentation is not large at all.

That's assuming the crawlers haven't ingested it all already...

Anything that makes email development easier is great I guess, but have personally found MJML great for solving the issues you'd run into, and not sure I want yet another abstraction layer on top of that which makes it more limited...

Very funny and brutally honest!

A more native open-source version:

https://github.com/0xCUB3/wBlock

+1 for Raycast Floating Notes. Looking forward to their version 2.0 which will support tabbing and markdown. Should make it even better.