Search Results - Mikita Balesni

  • Showing 1 - 9 results of 9
Refine Results
  1. 1
    The Two-Hop Curse: LLMs trained on A->B, B->C fail to learn A-->C

    The Two-Hop Curse: LLMs trained on A->B, B->C fail to learn A-->C by Mikita Balesni, Korbak, Tomek, Evans, Owain

    Published in arXiv.org
    Get full text
    Article
    Save to List
    Saved in:
  2. 2
    Large Language Models can Strategically Deceive their Users when Put Under Pressure

    Large Language Models can Strategically Deceive their Users when Put Under Pressure by Scheurer, Jérémy, Mikita Balesni, Hobbhahn, Marius

    Published in arXiv.org
    Get full text
    Article
    Save to List
    Saved in:
  3. 3
    Controlling Steering with Energy-Based Models

    Controlling Steering with Energy-Based Models by Mikita Balesni, Ardi Tampuu, Matiisen, Tambet

    Published in arXiv.org
    Get full text
    Article
    Save to List
    Saved in:
  4. 4
    Frontier Models are Capable of In-context Scheming

    Frontier Models are Capable of In-context Scheming by Meinke, Alexander, Schoen, Bronson, Scheurer, Jérémy, Mikita Balesni, Shah, Rusheb, Hobbhahn, Marius

    Published in arXiv.org
    Get full text
    Article
    Save to List
    Saved in:
  5. 5
    Honesty to Subterfuge: In-Context Reinforcement Learning Can Make Honest Models Reward Hack

    Honesty to Subterfuge: In-Context Reinforcement Learning Can Make Honest Models Reward Hack by McKee-Reid, Leo, Sträter, Christoph, Martinez, Maria Angelica, Needham, Joe, Mikita Balesni

    Published in arXiv.org
    Get full text
    Article
    Save to List
    Saved in:
  6. 6
    The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"

    The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A" by Berglund, Lukas, Tong, Meg, Kaufmann, Max, Mikita Balesni, Asa Cooper Stickland, Korbak, Tomasz, Evans, Owain

    Published in arXiv.org
    Get full text
    Article
    Save to List
    Saved in:
  7. 7
    Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs

    Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs by Laine, Rudolf, Chughtai, Bilal, Betley, Jan, Hariharan, Kaivalya, Scheurer, Jeremy, Mikita Balesni, Hobbhahn, Marius, Meinke, Alexander, Evans, Owain

    Published in arXiv.org
    Get full text
    Article
    Save to List
    Saved in:
  8. 8
    Taken out of context: On measuring situational awareness in LLMs

    Taken out of context: On measuring situational awareness in LLMs by Berglund, Lukas, Asa Cooper Stickland, Mikita Balesni, Kaufmann, Max, Tong, Meg, Korbak, Tomasz, Kokotajlo, Daniel, Evans, Owain

    Published in arXiv.org
    Get full text
    Article
    Save to List
    Saved in:
  9. 9
    Towards evaluations-based safety cases for AI scheming

    Towards evaluations-based safety cases for AI scheming by Mikita Balesni, Hobbhahn, Marius, Lindner, David, Meinke, Alexander, Korbak, Tomek, Clymer, Joshua, Buck Shlegeris, Scheurer, Jérémy, Stix, Charlotte, Shah, Rusheb, Goldowsky-Dill, Nicholas, Braun, Dan, Chughtai, Bilal, Evans, Owain, Kokotajlo, Daniel, Bushnaq, Lucius

    Published in arXiv.org
    Get full text
    Article
    Save to List
    Saved in:

Search Tools: