Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
Workaccount2
65 days ago
|
parent
|
context
|
favorite
| on:
Neural audio codecs: how to get audio into LLMs
Nothing is real understanding because we have no benchmark for understanding because we don't mechanistically know what understanding is. The best we have is people "vibe knowing" a benchmark that they made up on the spot.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: