Comment by visarga 3 months ago Solve the same task with ChatGPT, Gemini and Claude. If they agree, you can be reasonably sure. 3 comments visarga Reply caminante 3 months ago I'm not opposed to experimenting, but that's a a recipe for false confidence in a final decision. visarga 3 months ago Where they agree it shows the data supports that answer - not necessarily that it is true, where they disagree it shows you need to hedge. That's useful. caminante 3 months ago This is so wrong!e.g., if you had a heart condition, you can't just poll three LLMs and be "reasonably sure" you've properly diagnosed the ailment.
caminante 3 months ago I'm not opposed to experimenting, but that's a a recipe for false confidence in a final decision. visarga 3 months ago Where they agree it shows the data supports that answer - not necessarily that it is true, where they disagree it shows you need to hedge. That's useful. caminante 3 months ago This is so wrong!e.g., if you had a heart condition, you can't just poll three LLMs and be "reasonably sure" you've properly diagnosed the ailment.
visarga 3 months ago Where they agree it shows the data supports that answer - not necessarily that it is true, where they disagree it shows you need to hedge. That's useful. caminante 3 months ago This is so wrong!e.g., if you had a heart condition, you can't just poll three LLMs and be "reasonably sure" you've properly diagnosed the ailment.
caminante 3 months ago This is so wrong!e.g., if you had a heart condition, you can't just poll three LLMs and be "reasonably sure" you've properly diagnosed the ailment.
I'm not opposed to experimenting, but that's a a recipe for false confidence in a final decision.
Where they agree it shows the data supports that answer - not necessarily that it is true, where they disagree it shows you need to hedge. That's useful.
This is so wrong!
e.g., if you had a heart condition, you can't just poll three LLMs and be "reasonably sure" you've properly diagnosed the ailment.