Tyler Collins
Research computing consultant, Canada
I help researchers turn computational problems into reliable software and workflows: HPC systems, Python tooling, EEG/MEG pipelines, getting more out of the hardware you already have, and helping scientific teams use AI coding agents well.
Recent writing
All writing-
What researchers ask about agents
Most questions at Tuesday's intro to ARC session were about trust and verification, not which model is smartest. The answers are mostly old research habits.
-
Your dotfiles repo should be private now
Keeping your config in a git repo isn't new. What's new is an agent that can set up a fresh machine from Markdown instructions, and a private repo that can hold your whole working setup.
-
Your research isn't Navier–Stokes
Navier–Stokes was close to the best possible problem for an AI agent. Most research doesn't look like that, so the specifying and checking is still your job.
-
Think out loud with local Whisper
Talking through a problem is a good way to organize your thoughts, and OpenWhispr with a local Whisper model lets you capture it for free on hardware you probably already have.
-
Grants will need a line for tokens
More research money is going to LLM tokens. I predict Canadian granting agencies will add a token allocation tied to sovereign, safe infrastructure.