EDITED v. 10
AlignGeist
Building Evaluations for AI Alignment (Safety) Research with the insights of the humanities
| 1 | 11 | 8 |
|---|
Research
Event finish
JOINED
5 days ago
~
CarmiellaSalz
Challenge shared
Tap here to review.
5 days ago
~
CarmiellaSalz
Start
GLAMhack 2026
We created an evaluation on how do you predict AI will bridge the gap between digital and reality. The questions ranged on embodiment, robotics, what are the risks or challenges. We struggled to get Apertus, Claude, ChatGPT, Mistral, Grok, set up, had to implement workarounds, but managed to connect them all including Apertus 70B. Tomorrow we will show our most interesting results. (Paraphrasing the check-in report)