Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
c1ccccc1
on Nov 17, 2022
|
parent
|
context
|
favorite
| on:
AI found a bug in my code
If the context window is finite, then LLMs actually are Markov chains. It's just that they're a much more efficient way of representing transition probabilities than storing them all in a giant lookup table.
nextaccountic
on Nov 17, 2022
[–]
What's a LLM? It isn't a logic learning machine, right? Or a load linked Markov
You mean, a large language model?
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
