zlacker

>>mef+(OP)
I recently saw a new LLM that was fooled by "20 pounds of bricks vs 20 feathers". These are not reasoning machines.

>>peterm+B3
20 feathers?

>>fzzzy+V4
Yes, Claude 4 Sonnet just said they both weight 20 pounds. UPD. and so did Gemini 2.5 Flash. And MS Copilot in "Think deeper" mode.