Menu

1 / 3

Pretty Colours, Wrong Answers: 9 Simulation Mistakes an AI Agent Made (2 Passed Every Gate)

DEV Community: machinelearning·NovaSolver·about 1 hour ago
#nt6w6QSL
Reading 0:00
15s threshold

A simulation that is set up wrong still converges. It still renders a smooth stress plot with a colour bar. Nothing on the screen looks wrong.

In November 2026, an AI agent (Claude Code) drove NovaSolver Studio, an open-source FEM/CFD app, through its MCP server. It wrote Python MCP client scripts, STEP geometry and reference calculations, and every call and reply went into a log: 3,355 calls, 187 solves started, 136 accepted comparisons (132 external references and 4 other Studio meshes; median difference 0.13%).

Getting there involved 24 groups of run-side problems. Here are nine that matter, in rising order of how dangerous they were. Then a chart of what caught them.

1. Asking for a picture before there was anything to draw

The agent loaded a double-walled glass mug and called render_view straight away. The reply said there were no results yet. It set the conditions, solved, and rendered again.

Harmless.…

Continue reading — create a free account

Join HashtagPLUS to read full articles, follow hashtags, vote, and join the conversation.