He recommends drafting papers as LaTeX directly inside codebases.
My advice to PhD students in 2026: 1) If your advisor hasn't logged >100 hours in a modern agentic IDE, stop listening to your advisor. 2) Write your next paper *inside your codebase* as a .tex (with 80 char word-wrap). Force your advisor to read and make edits inside the IDE.
@jon_barron most "advisors" have gotten back to IDEs and the workflows are moving back into text/markdown.
My advice to PhD students in 2026: 1) If your advisor hasn't logged >100 hours in a modern agentic IDE, stop listening to your advisor. 2) Write your next paper *inside your codebase* as a .tex (with 80 char word-wrap). Force your advisor to read and make edits inside the IDE.
He recommends drafting papers as LaTeX directly inside codebases.
My advice to PhD students in 2026: 1) If your advisor hasn't logged >100 hours in a modern agentic IDE, stop listening to your advisor. 2) Write your next paper *inside your codebase* as a .tex (with 80 char word-wrap). Force your advisor to read and make edits inside the IDE.
Many users rejected urging PhD students to demand advisors experienced with agentic IDEs, arguing that such tools are fleeting trends and advisors should instead offer enduring research taste and judgment.