Hugging Face's logo
Dongyoon Hahm's picture
2 1

Dongyoon Hahm

Hahmdong
https://hahmdy.github.io

AI & ML interests

AI Safety

Recent Activity

upvoted a paper 1 day ago
Alignment Tampering: How Reinforcement Learning from Human Feedback Is Exploited to Optimize Misaligned Biases
submitted a paper 1 day ago
Alignment Tampering: How Reinforcement Learning from Human Feedback Is Exploited to Optimize Misaligned Biases
authored a paper 2 days ago
Alignment Tampering: How Reinforcement Learning from Human Feedback Is Exploited to Optimize Misaligned Biases
View all activity

Organizations

None yet