Announcing AIXI Labs — LessWrong
We are starting AIXI Labs, an AI safety org focused on algorithmic information theory (AIT), continual reinforcement learning (RL), and in particular…
x Announcing AIXI Labs — LessWrong Agent Foundations AI Safety AIXI Solomonoff induction AI Personal Blog 85 Announcing AIXI Labs by Cole Wyeth , Aram Ebtekar , michaelcohen , Matthias Dellago , Marcus Hutter 22nd Jul 2026 5 min read 9 85 We are starting AIXI Labs, an AI safety org focused on algorithmic information theory (AIT), continual reinforcement learning (RL), and in particular the eponymous AIXI. We aim to strengthen the technical case that developing artificial super intelligence (ASI) poses an X-risk while (in parallel) developing and prototyping theoretically-founded mitigations. (
saved by
related reading
- LessWronglesswrong.com
- What is AIXI?jan.leike.name
- Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com
- The case for ensuring that powerful AIs are controlled — LessWronglesswrong.com
- The Case Against AI Control Research — LessWronglesswrong.com
- AI Safety: A Short FAQ for Mathematiciansalkjash.github.io
- Sequent: scale and automation for higher confidence in alignment — AI Alignment Forumalignmentforum.org
- I am worried about near-term non-LLM AI developments — LessWronglesswrong.com
- Core views on AI safety: When, why, what, and how \ Anthropicanthropic.com
- Sequent: Scale and Automation for Higher Confidence in Alignment — Sequentsequent.org
- Core views on AI safety: When, why, what, and how \ Anthropicanthropic.com
- Notes on Existential Risk from Artificial Superintelligencemichaelnotebook.com