Visual reasoning and the challenge of diagnosing engineering failures
Citing MechReason, a post says models fail most at connecting the different kinds of evidence engineers use to diagnose failures.
TLDR
A post describes visual reasoning through an engineering example: connecting drawings, thermal images, simulations and inspections to identify what went wrong and find a solution. The author cites MechReason as showing that models fail most at this stage, and says their team at ElorianAI is building models to reason like engineers.
Combined views
—
1 Source, first seen ago
— likes— comments— saves— reposts
