Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
furyofantares
26 days ago
|
parent
|
context
|
favorite
| on:
Diffusion models are real-time game engines
Short clips are the only way a human will make any errors determining which is which.
darrinm
26 days ago
[–]
More relevant is if by _playing_ it they couldn’t tell which is which.
Jensson
26 days ago
|
parent
[–]
They obviously can within seconds, so it wouldn't be a result. Being able to generate gameplay that looks right even if it doesn't play right is one step.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: