Hacker News Reader

Comment by levocardia | Hacker News Reader

What's even more uncanny is that it recognizes that it briefly went into a paragraph of rambling nonsense (that was seemingly still following your system prompt!). And almost seems embarrassed about it.

View on HN

Embarrassment seems to be the default state whenever you question ChatGPT or any of its messages. It will apologise, only to continue making the same error. This is common when it gives you code with obvious errors or just mirror code you gave it.

I couldn't stand that so my custom instructions tell it to never apologize.

Same. I hate obsequious software.

That happened because the last message is after the fix and it received the garbled history as the prompt.

All it's doing is noticing that makes no sense and saying so. How could it not recognize it? The additional message is an entirely new instance not a thing that has memory.

>All it's doing is noticing that makes no sense and saying so. How could it not recognize it?

you say that like it's the simplest thing in the world. it really amazes me how quickly people acclimate to this mind-blowing tech.

I just mean, given that LLMs exist this isn't a surprising result. It only looks surprising because the UI makes you forget that each prompt is a completely new universe to the model.

I wouldn't call a step in a history-aware conversation a completely new universe. By that logic, every single time a token is generated is a new universe even though the token is largely dependent on the prompt, which includes custom instructions, chat history, and all tokens generated in the response so far.

Well, I would have also said or thought that each token actually is a new universe in a sense. You could rotate between different LLMs for each token for example or instances of the same LLM or branch into different possibilities. Input gets cycled again as a whole.

I’m not sure how you are using the term “history aware”, Would a time series forecasting tool be history aware ?

The LLM has very little memory between two tokens of the same message (there might be a little in the sampling algorithm), so it should be equally capable of noticing an error in the same message as a new one.

Reply on news.ycombinator.com