PhD student at @ucl-dark. Interested in understanding LLM fine-tuning, AI safety and (super)alignment.
- London
-
10:40
(UTC) - https://robertkirk.github.io/
- @_robertkirk
Highlights
- Pro
Tomáš Gavenčiak
gavento
Researcher at @acsresearch working on AI theory of alignment, game theory, and complex LLM agent interactions.
Alignment of Complex Systems Prague