← People

Chan Jun Shern

Source-listed: Member of Technical Staff · Anthropic

  • Information retrieval
  • Evaluation

Selected work

5
  1. PaperBench: Evaluating AI’s Ability to Replicate AI ResearchContributor · 2025
  2. MLE-bench: Evaluating Machine Learning Agents on Machine Learning EngineeringContributor · 2024
  3. GPT-4o System CardContributor · 2024
  4. Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI BenchmarkContributor · 2023
  5. Few-shot Adaptation Works with UnpredicTable DataFirst author · 2023