pith. sign in

Tristan Hume

Identifiers

  • name variant Tristan Hume 0.60 · backfill

Papers (12)

  1. Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet cs.AI · 2026 · author #17
  2. Specific versus General Principles for Constitutional AI cs.CL · 2023 · author #31
  3. Measuring Faithfulness in Chain-of-Thought Reasoning cs.AI · 2023 · author #25
  4. The Capacity for Moral Self-Correction in Large Language Models cs.CL · 2023 · author #38
  5. Discovering Language Model Behaviors with Model-Written Evaluations cs.CL · 2022 · author #52
  6. Constitutional AI: Harmlessness from AI Feedback cs.CL · 2022 · author #43
  7. Measuring Progress on Scalable Oversight for Large Language Models cs.HC · 2022 · author #42
  8. Toy Models of Superposition cs.LG · 2022 · author #2
  9. Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned cs.CL · 2022 · author #23
  10. Language Models (Mostly) Know What They Know cs.CL · 2022 · author #15
  11. Scaling Laws and Interpretability of Learning from Repeated Data cs.LG · 2022 · author #10
  12. Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback cs.CL · 2022 · author #19

Mentions

  • 2310.13798 #31 · arxiv_oai · confidence 0.70 Tristan Hume
  • 2307.13702 #25 · arxiv_oai · confidence 0.70 Tristan Hume
  • 2302.07459 #38 · arxiv_oai · confidence 0.70 Tristan Hume
  • 2212.09251 #52 · arxiv_oai · confidence 0.70 Tristan Hume
  • 2212.08073 #43 · arxiv_oai · confidence 0.70 Tristan Hume
  • 2209.07858 #23 · arxiv_oai · confidence 0.70 Tristan Hume
  • 2207.05221 #15 · arxiv_oai · confidence 0.70 Tristan Hume
  • 2209.10652 #2 · arxiv_oai · confidence 0.70 Tristan Hume
  • 2204.05862 #19 · arxiv_oai · confidence 0.70 Tristan Hume
  • 2605.29358 #17 · arxiv_oai · confidence 0.70 Tristan Hume
  • 2205.10487 #10 · arxiv_oai · confidence 0.70 Tristan Hume
  • 2211.03540 #42 · arxiv_oai · confidence 0.70 Tristan Hume

Frequent Coauthors