Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
radarsat1
3 months ago
|
parent
|
context
|
favorite
| on:
Why do LLMs freak out over the seahorse emoji?
Aside but I find it really interesting how looking at the layers "approach" the answer at a specific token position like this feels a lot like an iterative optimizer taking steps to converge on a solution.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: