Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
dragonwriter
on Nov 28, 2023
|
parent
|
context
|
favorite
| on:
Let's try to understand AI monosemanticity
That's like anthropomorphizing utility functions in place of the humans that (are conjectured to) have them, isn't it?
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: