What you should be able to do
Write testable hypotheses
Design baselines
Run ablations
Document negative results
Every module is now a full lesson.
Experiment design
Turn a vague idea into a falsifiable test with a baseline and explicit evidence standard.
Baselines
Build a working mental model of Baselines then connect it to implementation evaluation and production trade-offs.
Ablation
Build a working mental model of Ablation then connect it to implementation evaluation and production trade-offs.
Reproducibility
Build a working mental model of Reproducibility then connect it to implementation evaluation and production trade-offs.
Error analysis
Build a working mental model of Error analysis then connect it to implementation evaluation and production trade-offs.
Research writing
Build a working mental model of Research writing then connect it to implementation evaluation and production trade-offs.
Projects that prove the skill
Innovation lab study
Use a baseline first then instrument the result and document failure cases.
design with cortex →Policy replay experiment
Use a baseline first then instrument the result and document failure cases.
design with cortex →Retrieval ablation
Use a baseline first then instrument the result and document failure cases.
design with cortex →How progress is judged
Evidence quality
Evidence should come from code, results, explanation quality and the ability to identify when an approach should not be used.
Reproducibility
Evidence should come from code, results, explanation quality and the ability to identify when an approach should not be used.
Clarity
Evidence should come from code, results, explanation quality and the ability to identify when an approach should not be used.
Turn the track into a personal plan.
Cortex can break this path into daily sessions and adjust based on completed lessons, interview results and your saved learning goals.
Ask Cortex to plan it →