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

The probability that the broken clock is right is straightforwardly 2/1440 = 0.001 = 0.1%, innit?



Clock correctness is relative. If the antique windup clock in your living room is off by 5 minutes, it's still basically right. But if the clock in your smartphone is 5 minutes off, something has clearly gone wrong.


To the second? To the millisecond? What are we wanting here? You're missing the point.

But I'll play this silly game: ChatGPT is not incorrect 99.9% of the time.


Nor is it only incorrect one billionth of the time, as you seem to be indicating through your hypotheticals. Depending on what I've asked it about, it can be incorrect at an extremely high rate.


That is definitely not what I am indicating. I'm pointing out the absurdity of speaking of probabilistic things in absolutes.

Yes, ask an LLM to multiply a few numbers together and you will get around 100% failure rate.

The same goes for quotes, citations, website addresses, and most numerical facts.

The failures are predictable. That means the models can be augmented with external knowledge, Python or JS interpreters, etc.




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

Search: