Hacker News new | past | comments | ask | show | jobs | submit login

Answer from GPT-4 Turbo: If two trains are 30 miles apart and are approaching each other at a speed of 10 mph each, their combined approach speed is 20 mph (10 mph + 10 mph). To find the time it takes for them to meet, you divide the distance by their combined speed: 30 miles / 20 mph = 1.5 hours Therefore, it will take 1.5 hours before they meet (or crash into each other, as stated in the question). Two trains on separate tracks, 30 miles from each other are approaching each other, each at a speed of 10 mph. How long before they crash into each other?



Which is wrong, no? Trains on separate tracks don't crash into each other.

That trips up a significant portion of humans too though


Inconclusive. The model includes a disclaimer: "(or crash into each other, as stated in the question)." LLMs often take a detour and spill their guts without answering the actual question. Here's a hint suggesting that user input influences the internal world representation much more significantly than one might expect.


That disclaimer is only there with GPT4-turbo. I assume I could experiment for a while and find something similar that trips it up fully.


Assuming the trains aren't wide enough to collide even if they are on separate tracks


Which would be quite unusual for normal trains. That being said, the question implies that they will crash into each other, so you could argue that this is a valid assumption anyway.


Mine only says: "The trains will crash into each other in 1.5 hours."




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: