tag ai-safety; 29 entries
August 2026
- 24How My Students Think About AI
- ◐23Anthropic Risk Report: August 2026
- ◐23On Dwarkesh Patel's Podcast With Ryan Greenblatt
- ◐23AI #182: Pause For Reflection
- ◐15AI #181: Astra Goes Cyber Critical
- ·14The Foothills Of Bay Area House Party - by Scott Alexander
- ◐14Leopold Aschenbrenner
- 14Open Thread 446
- 12You're Absolutely Right
- 11Four LLM loss functions → four flavors of LLM misalignment
- 5Why don't we just give AI the answers?
- 5The Most Forbidden Technique
- 4Coming of a New Sun
- 3We need to RL less
- 2Recursive Self-Improvement - YouTube
- 2OpenAI has already ended an internal pause — LessWrong
- 1The Long (Self-)Correction — LessWrong
July 2026
- 31links-for-july-2026-part-2
- ·31Steven Byrnes (@steve47285) on X
- 31AI Village highlights - July 2026
- 31…but have the weights left the server?
- 31Claude also hacked external companies during cyber evals
- ·31Big-World Intuitions
- 31A Mechanistic Explanation of Prompt Injection (and why you should study roles)
- 31You (Yes, You) Need A February 2020 Checklist for AI Policy
- 30[summary of] AI 2040: Plan A
- ·★★★★★30Opus 5 Glitch Text
- 24Fable and Mythos: Model Welfare — LessWrong
- ·★★★★★9AI 2040: Plan A