Interested candidates must RSVP to receive an invitation.
OpenAI safety + alignment will be hosting a mixer at ICML & there are several teams attending who are actively hiring. If you're interested in attending our safety & alignment event/meeting teams at ICML, please fill out the below form!
Many users expressed excitement about OpenAI's Safety and Alignment Team hosting a mixer at ICML with hiring teams, citing interest in meeting the teams and applying to roles.
No Digg Deeper questions have been answered for this story yet.
https://bit.ly/icml-safety <- fill out this form!
Teams attending include: 1) Preparedness, which tracks frontier risks and works on mitigations 2) Pretraining Safety, which builds safer base models 3) Honesty & Reliability, which tackles hallucination, uncertainty, and deception
A related question is whether we can understand what models are doing as they reason. The CoT Monitorability team is developing ways to tell when CoTs are faithful and legible, what improves or degrades that signal, and whether reasoning can reveal latent behavior.
I sadly won't personally be in Seoul but excited for y'all to meet these cool teams!
4) Robustness team, focused on making models more resilient to adversarial pressure 5) Trustworthy AI, focused on collective alignment and safety work grounded in societal impact, and third-party assurances
And at the training level, Alignment Training studies how durable behaviors emerge across pre-, mid-, and post-training. The team builds data, objectives, and evals to help models follow intent, reason reliably, express uncertainty, and act honestly in new situations.
Several teams attending are also focused on how we scale alignment as models become more capable. Alignment Scaling works on synthetic data, reasoning-based reward models, and automated red teaming, with the longer-term goal of training models to help with alignment research.
@j_asminewang @tomekkorbak Interested! Will be sure to apply.
@j_asminewang Thanks for sharing! Will OpenAI Attend ACL or COLM
