Get my own profile
Co-authors
- Neel NandaMechanistic Interpretability Team Lead, Google DeepMindVerified email at deepmind.com
- Alexandre VariengienENS de Lyon & EPFLVerified email at ens-lyon.fr
- Aengus LynchUniversity College London, MATSVerified email at ucl.ac.uk
- Senthooran RajamanoharanGoogle DeepMindVerified email at google.com
- Janos KramarDeepMindVerified email at google.com
- Jacob SteinhardtStanford UniversityVerified email at cs.stanford.edu
- Rohin ShahResearch Scientist, Google DeepMindVerified email at deepmind.com
- Adriŕ Garriga-AlonsoResearch Scientist, FAR AIVerified email at far.ai
- Connor KissaneIndependentVerified email at richmond.edu
- Robert KrzyzanowskiPoseidon ResearchVerified email at poseidonresearch.com
- Nicholas CarliniGoogle DeepMindVerified email at google.com
- Daniel PalekaETH ZurichVerified email at inf.ethz.ch
- Anca D DraganAssistant Professor at UC Berkeley // Director, AI Safety and Alignment, Google DeepMindVerified email at berkeley.edu
- Aaquib SyedMATS 5.0 | Student, University of MarylandVerified email at umd.edu
- Rhys GouldMathematics Undergraduate, University of CambridgeVerified email at cam.ac.uk
- Euan OngResearch Assistant, University of CambridgeVerified email at cam.ac.uk
- Joseph Isaac BloomUK AI Safety InstituteVerified email at dsit.gov.uk
- Rowan WangVerified email at rdwrs.com
- Stepan ShabalinGeorgia Institute of TechnologyVerified email at gatech.edu