allenleee
- Karma
- 7,390
- Created
- 11 years ago
About
interpretability, rl, ai safetyhttps://fp8.vercel.app
Recent Submissions
- 1. ▲ Meta's Infrastructure Team Needs a Culture Reset (newsletter.semianalysis.com)
- 2. ▲ External Commentary on LLM Global Workspace Representations [pdf] (www-cdn.anthropic.com)
- 3. ▲ Reflect Open – a new chapter for Reflect (reflect.app)
- 4. ▲ AirPosture – AirPods as AI posture coach (Open source) (airposture.github.io)
- 5. ▲ Show HN: AirPosture – Open-Source Posture Coach Using AirPods (github.com)
- 6. ▲ FPGA Development Deep Dive (modretro.com)
- 7. ▲ Looking for Backdoors in Jane Street LLMs (alignmentforum.org)
- 8. ▲ The West Is Losing Taiwan (allenv0.github.io)
- 9. ▲ Measuring LLMs' ability to develop exploits (red.anthropic.com)
- 10. ▲ From Open Source Software to Open Source Strategy (p3institute.substack.com)