Lessons From Red-teaming Auto-review, OpenAI's Blocking Monitor — LessWrong
This work and the report were done by Giovanni Occhipinti, as part of the ERA fellowship and mentored by Monika Jotautaitė (Apollo Research). …
Topics: Models
This work and the report were done by Giovanni Occhipinti, as part of the ERA fellowship and mentored by Monika Jotautaitė (Apollo Research). …
Topics: Models