AI ALIGNMENT FORUM
AF

ThomasW

Center for AI Safety

Posts

Sorted by New

9[MLSN #9] Verifying large training runs, security risks from LLM access to APIs, why natural selection may favor AIs over humans2mo

0

10[MLSN #8] Mechanistic interpretability, using law to inform AI alignment, scaling laws for proxy gaming3mo

0

24Announcing the Introduction to ML Safety course10mo

3

20$20K In Bounties for AI Safety Public Materials10mo

0

29Examples of AI Increasing AI Progress10mo

4

19Open Problems in AI X-Risk [PAIS #5]1y

2

17Perform Tractable Research While Avoiding Capabilities Externalities [Pragmatic AI Safety #4]1y

0

19Complex Systems for AI Safety [Pragmatic AI Safety #3]1y

1

41A Bird's Eye View of the ML Field [Pragmatic AI Safety #2]1y

2

29Introduction to Pragmatic AI Safety [Pragmatic AI Safety #1]1y

0

Wiki Contributions

Comments