Into AI Safety
intoaisafety.bsky.social
Official Bluesky account for the Into AI Safety podcast - available on all podcast listening platforms! https://kairos.fm/intoaisafety
👤 Joined on 26 January 2025
26
Followers
10
Following
23
Total Posts
📜 Kullanıcı Geçmişi
- 26 Oca 2025, 19:54
🎉 Bluesky'e katıldı - İlk kullanıcı adı:
@intoaisafety.bsky.social
🚫 Blokladığı Kullanıcılar
❤️ Beğendiği Gönderiler
Super happy to share HumanAgencyBench, which takes steps towards understanding the impact of chatbot interactions on huma agency. Working with @jacyanthis.bsky.social (and the team) has been fantastic, and I'd happily do it again. If you have the chance to work with him, don't pass it up!
Show Post
LLM agents are optimized for thumbs-up instant gratification. RLHF -> sycophancy We propose human agency as a new alignment target in HumanAgencyBench, made possible by AI simulation/evals. We find e.g., Claude most supports agency but also most tries to steer user values 👇 arxiv.org/abs/2509.08494
Show Post
🚨 New episode is out: "One Big Bad Bill" - breaking down AI's relevance to Trump's bill. We cover automated fraud detection, government data consolidation, and a 10-year ban on state AI regulation. Find us on Spotify, Apple Podcasts, YouTube, or wherever you listen (links in thread).
Show PostNEW EPISODE: "Making Your Voice Heard w/ Tristan Williams & Felix de Simone" - where we explore how everyday citizens can influence AI policy through effective communication with legislators 🎙️ kairos.fm/intoaisafety... Listen on Spotify, Apple Podcasts, YouTube, or wherever you get your podcasts!
Show Post