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-
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.
-
Send your agent a screenshot
Agents only know the dashboards they were trained on. When menus keep moving or a UI looks wrong, a screenshot gives the agent what's actually on your screen.
-
Get a second opinion from another model
Models are tuned to write code differently. If you have the tokens, having one review another's work is basic hygiene, and personas take the idea further.