allenleee
- Karma
- 7,391
- Created
- 11 years ago
About
interpretability, rl, ai safetyhttps://allenlee.site
Recent Submissions
- 1. ▲ LLM Time Travel Visualization Proposal (gwern.net)
- 2. ▲ Reverse-Engineering Jane Street's ASIC (mooofin.github.io)
- 3. ▲ How Russia Continues to Reinvent the One-Way Attack Drone (csis.org)
- 4. ▲ Meta's Infrastructure Team Needs a Culture Reset (newsletter.semianalysis.com)
- 5. ▲ External Commentary on LLM Global Workspace Representations [pdf] (www-cdn.anthropic.com)
- 6. ▲ Reflect Open – a new chapter for Reflect (reflect.app)
- 7. ▲ AirPosture – AirPods as AI posture coach (Open source) (airposture.github.io)
- 8. ▲ Show HN: AirPosture – Open-Source Posture Coach Using AirPods (github.com)
- 9. ▲ FPGA Development Deep Dive (modretro.com)
- 10. ▲ Looking for Backdoors in Jane Street LLMs (alignmentforum.org)