FAR.AI
far.ai
Frontier alignment research to ensure the safe development and deployment of advanced AI systems.
👤 Joined on 27 November 2024
233
Followers
1
Following
542
Total Posts
📜 Kullanıcı Geçmişi
- 27 Kas 2024, 01:49
🎉 Bluesky'e katıldı - İlk kullanıcı adı:
@far-ai.bsky.social - 06 Ara 2024, 00:05
✏️ Kullanıcı adı değişti:
@far-ai.bsky.social→@far.ai
🚫 Blokladığı Kullanıcılar
Bu kullanıcının blokladığı kullanıcı bulunamadı.
❤️ Beğendiği Gönderiler
If you tell an AI to convince someone of a true vs. false claim, does truth win? In our *new* working paper, we find... ‘LLMs can effectively convince people to believe conspiracies’ But telling the AI not to lie might help. Details in thread
Show PostCome chat with us about our AI Safety papers at #NeurIPS2024! 12/11: 💥Catastrophic Goodhart: overoptimization in RLHF 12/12: ⚙️ Analysing the Generalisation and Reliability of Steering Vectors 12/12: 🌀 Hypothesis Testing the Circuit Hypothesis in LLMs 12/13: 🔬 InterpBench 🧵👇
Show Post