Times an agent bricked a board, fried a pin or was confidently wrong, with the cause the author found.
Newest first, as we log them.
Filtered by
2 mo ago
XDA's Adam Conway ran the same ESP32 wiring prompt 15 times across Claude Sonnet 5 and Opus 5. With a vague prompt, Sonnet put a display's DC line on strapping pin GPIO2 in 3 of 6 runs, twice after naming the rule. Opus never did, though one run misstated the rule. He writes that naming the exact board helped both.
3 mo ago
Anthropic's red team had Claude, GPT, Gemini and other models drive robots, mostly in simulation plus a real Unitree Go2. The team reports that Opus 4.6 misjudged where a trash can was and the Go2 dragged it. Grok 4.1 Fast headed for a table reflected in a glass door, and no model completed an office loop on vision alone.
5 mo ago
Alice Plante had Claude write the code and choose actions for a SunFounder PiCar-X on a Raspberry Pi 5 and a FrodoBots Earth Rover. The Earth Rover's commands went through a cloud relay while Opus took about ten seconds to answer, and it drove into trees. A small binary on the rover cut command latency to under 10 ms.
