Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

On some level this makes sense, but on the other hand LLMs already have perfect recall of thousands of symbols built into them, which is what pencil and paper gives to a human test taker.


If only context recall was actually perfect! The data is certainly stored well, accurately accessing the right part... maybe worse than a human :D.


If you're not doing clever hacks for very long windows, I thought a basic design fed in the entire window and it's up to the weights to use it properly.




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

Search: