Hi everyone, Iโm Jean โ a Total Rewards professional currently exploring the AI Safety space.
Iโve spent the last few years designing incentive systems for humans: compensation structures, recognition programs, performance frameworks. The core challenge is always the same โ how do you translate an organizationโs values into measurable criteria, without creating perverse incentives that undermine the very goals youโre trying to reach?
At some point I realized this is exactly the alignment problem.
The more I read about RLHF, reward hacking, and Constitutional AI, the more I recognized patterns Iโd already encountered in my work. Goodhartโs Law isnโt a theoretical concern for me โ Iโve watched it play out in bonus systems. The tension between extrinsic and intrinsic motivation? Iโve navigated that in practice.
Iโm at the beginning of this transition. Iโve just started working through AI Safety Fundamentals and Iโm looking to connect with people thinking seriously about the human side of alignment โ governance, evaluation, values specification.
If you work at the intersection of behavioral systems and AI alignment, or if you think Total Rewards intuitions could translate meaningfully into this field, Iโd genuinely love to talk.
Hi everyone, Iโm Jean โ a Total Rewards professional currently exploring the AI Safety space.
Iโve spent the last few years designing incentive systems for humans: compensation structures, recognition programs, performance frameworks. The core challenge is always the same โ how do you translate an organizationโs values into measurable criteria, without creating perverse incentives that undermine the very goals youโre trying to reach?
At some point I realized this is exactly the alignment problem.
The more I read about RLHF, reward hacking, and Constitutional AI, the more I recognized patterns Iโd already encountered in my work. Goodhartโs Law isnโt a theoretical concern for me โ Iโve watched it play out in bonus systems. The tension between extrinsic and intrinsic motivation? Iโve navigated that in practice.
Iโm at the beginning of this transition. Iโve just started working through AI Safety Fundamentals and Iโm looking to connect with people thinking seriously about the human side of alignment โ governance, evaluation, values specification.
If you work at the intersection of behavioral systems and AI alignment, or if you think Total Rewards intuitions could translate meaningfully into this field, Iโd genuinely love to talk.
Happy to be here.