Re:Gemini 3 Deep Think
by simonw on Friday February 13, 2026 @10:30AM
(#47003794)
Not without people later saying "you shared that on Hacker News last year clearly the AI labs are training for it now!"
[ Parent
| on HN ]
Re:Gemini 3 Deep Think
by buttered_toast on Friday February 13, 2026 @10:54AM
(#47004134)
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.
Here's what it gave me for a kakapo on a skateboard https://gist.github.com/simonw/5e2041c32333effd090e3df42b64d...
Re:Gemini 3 Deep Think
by buttered_toast on Friday February 13, 2026 @11:40AM
(#47004667)
Thank you!