| user: | allenleee |
| created: | November 5, 2014 |
| karma: | 7.4k |
| about: | interpretability, rl, ai safety https://fp8.vercel.app |
| 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. | |
| 6. | 60 days ago | discuss |
| 7. | 60 days ago | discuss |
| 8. | FPGA Development Deep Dive(modretro.com) |
| 9. | Looking for Backdoors in Jane Street LLMs(alignmentforum.org) |
| 10. | The West Is Losing Taiwan(allenv0.github.io) |
| 11. | Measuring LLMs' ability to develop exploits(red.anthropic.com) |
| 12. | From Open Source Software to Open Source Strategy(p3institute.substack.com) |
| 13. | RTX 5090 and M4 MacBook Air: Can It Game?(scottjg.com) |
| 14. | Test your interpretability techniques by de-censoring Chinese models(alignmentforum.org) |
| 15. | The state of AI safety in four fake graphs(lesswrong.com) |
| 16. | Modeling the AGI Economy(continuations.com) |
| 17. | |
| 18. | |
| 19. | YC's Formula for Startup Manufacturing(investing101.substack.com) |