Year 2021 | Month Nov | Work done Wrote and submitted a paper to the SafeAI workshop Participated in the SERI ML Alignment Theory Scholars program Writing post on gradient hacking Nonlinear research analyst - AI safety ecosystem research Applied to the MLAB program (unsuccessfully) Did work on safe reinforcement learning project |
Dec | Applied to 4 PhD positions and one internship Interviewed 6 AI safety researchers for Nonlinear Finished AF post for SERI MATS program (22 AF, 25 LW) Asked a question on LW, 7 responses, 12 karma Wrote short LW post (6 karma) Worked on safe RL project | |
2022 | Jan | Applied to PhD positions Interviewed for PhD position Interviewed AI safety researchers (as interviewer) CHAI internship coding assessment Started using Anki |
Feb | Worked on posts about doing AI safety work Worked on Safe reinforcement learning project Interveiwed for CHAI internship Some math related to SERI project/gradient hacking |