Re:
by kenjackson on Wednesday July 09, 2025 @04:57PM
(#44514669)
It's possible that LLMs build ASTs internally for programming. I have no 1st hand data on this, but it would not surprise me at all.
[ Parent
| on HN ]
LLMs don't have memory, so they can't build anything. Insofar as they produce correct results, they have implicit structures corresponding to ASTs built into their networks during training time.
Re:
by kenjackson on Thursday July 10, 2025 @10:50AM
(#44521744)
"LLMs don't have memory"
That's interesting. Is there research into adding memory or has it been proven that it provides no pragmatic value over any context it outputs?