News for hackers. Stuff that matters.
Re:Claude 4 by felipeerias on Friday May 23, 2025 @01:19AM (#44070061)
Both Claude 4 Sonnet and Opus fail this one, even with extended thinking enabled, and even with a follow-up request to double-check their answers:

“What is heavier, 20 pounds of lead or 20 feathers?”

Re:Claude 4 by cdelsolar on Friday May 23, 2025 @09:57AM (#44072936)
chatgpt (whatever fast model they use) passed that after i told it to "read my question again"
Re:Claude 4 by ttoinou on Sunday May 25, 2025 @09:12AM (#44087567)
Can humans answer this correctly ? It is ambiguous