Drake Thomas
Identifiers
- name variant Drake Thomas 0.60 · backfill
Papers (2)
- Auditing language models for hidden objectives cs.AI · 2025 · author #30
- Catastrophic Goodhart: regularizing RLHF with KL divergence does not mitigate heavy-tailed reward misspecification cs.LG · 2024 · author #2
Mentions
- 2503.10965 #30 · arxiv_oai · confidence 0.70 Drake Thomas
- 2407.14503 #2 · arxiv_oai · confidence 0.70 Drake Thomas
Frequent Coauthors
- Adam Jermyn 1 shared papers
- Adam Pearce 1 shared papers
- Adri\`a Garriga-Alonso 1 shared papers
- Akbir Khan 1 shared papers
- Andy Shih 1 shared papers
- Austin Meek 1 shared papers
- Brian Chen 1 shared papers
- Carson Denison 1 shared papers
- Christopher Olah 1 shared papers
- Daniel Ziegler 1 shared papers
- Emmanuel Ameisen 1 shared papers
- Euan Ong 1 shared papers
- Evan Hubinger 1 shared papers
- Fabien Roger 1 shared papers
- Florian Dietz 1 shared papers
- Hoagy Cunningham 1 shared papers
- Jack Lindsey 1 shared papers
- Jan Kirchner 1 shared papers
- Jan Leike 1 shared papers
- Jeanne Salle 1 shared papers