Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
simonw
9 days ago
|
parent
|
context
|
favorite
| on:
Gemini 3 Deep Think
Not without people later saying "you shared that on Hacker News last year clearly the AI labs are training for it now!"
help
buttered_toast
9 days ago
[–]
Couldn't you just make up new combinations, or new caveats indefinitely to mitigate that? It would be nice to see maybe 3-4 good examples for validation. I'd do it myself, but I don't have $200 to play around with this model.
reply
simonw
9 days ago
|
parent
[–]
Here's what it gave me for a kakapo on a skateboard
https://gist.github.com/simonw/5e2041c32333effd090e3df42b64d...
reply
buttered_toast
9 days ago
|
root
|
parent
[–]
Thank you!
reply
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
