This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
LW
Login
1179
Zhijing Jin — LessWrong
Zhijing Jin
Posts
Sorted by New
Wikitag Contributions
Comments
Sorted by
Newest
Welcome to Apply: The 2024 Vitalik Buterin Fellowships in AI Existential Safety by FLI!
Zhijing Jin
2y
1
0
Thank you for spotting it! I just did the fix :).
Reply
9
Testing the Authoritarian Bias of LLMs
3mo
1
6
Why Reasoning Isn’t Enough: How LLM Agents Struggle with Ethics and Cooperation
4mo
0
6
Investigating Accidental Misalignment: Causal Effects of Fine-Tuning Data on Model Vulnerability
Ω
5mo
Ω
0
24
Corrupted by Reasoning: Reasoning Language Models Become Free-Riders in Public Goods Games
Ω
6mo
Ω
3
5
Welcome to Apply: The 2024 Vitalik Buterin Fellowships in AI Existential Safety by FLI!
2y
2
Thank you for spotting it! I just did the fix :).