Horizon Omega

@UCTYNJHoV2fMizko2MPZAgXA - 138 subscribers

HΩ – We advance AI safety through collaboration, research, and education.

Home Videos Live Playlists

Measuring Machine Consciousness – Cameron Berg

Measuring Machine Consciousness – Cameron Berg Horizon Omega

326 views - 4 weeks ago

Next Steps for AI Welfare Research – Jeff Sebo

Next Steps for AI Welfare Research – Jeff Sebo Horizon Omega

179 views - 1 month ago

Formal Guarantees for Frontier AI – Gagandeep Singh

Formal Guarantees for Frontier AI – Gagandeep Singh Horizon Omega

116 views - 2 months ago

Provably Safe Neural Network Controllers via Differential Dynamic Logic – Samuel Teuber

Provably Safe Neural Network Controllers via Differential Dynamic Logic – Samuel Teuber Horizon Omega

36 views - 3 months ago

Safe Learning Under Irreversible Dynamics via Asking for Help – Benjamin Plaut

Safe Learning Under Irreversible Dynamics via Asking for Help – Benjamin Plaut Horizon Omega

72 views - 7 months ago

When AI met AR – Clark Barrett

When AI met AR – Clark Barrett Horizon Omega

183 views - 8 months ago

Model-Based Soft Maximization of Suitable Metrics of Long-Term Human Power – Jobst Heitzig

Model-Based Soft Maximization of Suitable Metrics of Long-Term Human Power – Jobst Heitzig Horizon Omega

125 views - 9 months ago

Towards Safe and Hallucination-Free Coding AIs – GasStationManager

Towards Safe and Hallucination-Free Coding AIs – GasStationManager Horizon Omega

63 views - 10 months ago

Engineering Rational Cooperative AI via Inverse Planning and Probabilistic Programming, Tan Zhi Xuan

Engineering Rational Cooperative AI via Inverse Planning and Probabilistic Programming, Tan Zhi Xuan Horizon Omega

127 views - 1 year ago

Using PDDL Planning to Ensure Safety in LLM-based Agents – Agustín Martinez Suñé

Using PDDL Planning to Ensure Safety in LLM-based Agents – Agustín Martinez Suñé Horizon Omega

189 views - 1 year ago

Compact Proofs of Model Performance via Mechanistic Interpretability – Louis Jaburi

Compact Proofs of Model Performance via Mechanistic Interpretability – Louis Jaburi Horizon Omega

169 views - 1 year ago

The ‘World-System-AI’ Cybernetic Intelligence Alignment Problem

The ‘World-System-AI’ Cybernetic Intelligence Alignment Problem Horizon Omega

33 views - 1 year ago

Bayesian oracles and safety bounds – Yoshua Bengio

Bayesian oracles and safety bounds – Yoshua Bengio Horizon Omega

768 views - 1 year ago

Constructability: Designing plain-coded AI systems – Charbel-Raphaël Ségerie & Épiphanie Gédéon

Constructability: Designing plain-coded AI systems – Charbel-Raphaël Ségerie & Épiphanie Gédéon Horizon Omega

121 views - 1 year ago

Proving safety for narrow AI outputs – Evan Miyazono

Proving safety for narrow AI outputs – Evan Miyazono Horizon Omega

125 views - 2 years ago

Gaia: Distributed planetary-scale AI safety – Rafael Kaufmann

Gaia: Distributed planetary-scale AI safety – Rafael Kaufmann Horizon Omega

300 views - 2 years ago

Comparing National AI Policies with the AIDV Report

Comparing National AI Policies with the AIDV Report Horizon Omega

32 views - 2 years ago

We Are Not Prepared – Joe Rogero

We Are Not Prepared – Joe Rogero Horizon Omega

45 views - 2 years ago

Designing an International AI Safety & Ethics Network – Kyle Gracey

Designing an International AI Safety & Ethics Network – Kyle Gracey Horizon Omega

46 views - 2 years ago

AI alignment: Should It Be Just About Humans – Tse Yip Fai

AI alignment: Should It Be Just About Humans – Tse Yip Fai Horizon Omega

31 views - 2 years ago

AI safety R&D Accelerator Design – Orpheus Lummis

AI safety R&D Accelerator Design – Orpheus Lummis Horizon Omega

25 views - 2 years ago

Demo, feedback: AI Safety Benchmarking in Multi-objective Multi-agent Gridworlds – Pihlakas, Pyykkö

Demo, feedback: AI Safety Benchmarking in Multi-objective Multi-agent Gridworlds – Pihlakas, Pyykkö Horizon Omega

52 views - 2 years ago

Goodhart's law & invisibility of AI risk to science – Voita Kovarik

Goodhart's law & invisibility of AI risk to science – Voita Kovarik Horizon Omega

19 views - 2 years ago

Building with continuously trainable AI, Alternative to Pre-trained Deep Learning – Ali Al Ebrahim

Building with continuously trainable AI, Alternative to Pre-trained Deep Learning – Ali Al Ebrahim Horizon Omega

38 views - 2 years ago

Leveraging Global Talent for Technical AI safety Research - Apart's mode – Jason Hoelscher Obermaier

Leveraging Global Talent for Technical AI safety Research - Apart's mode – Jason Hoelscher Obermaier Horizon Omega

14 views - 2 years ago

Artificial Wisdom for Alignment – Madhusudhan Pathak

Artificial Wisdom for Alignment – Madhusudhan Pathak Horizon Omega

27 views - 2 years ago

SatisfIA – Updates From Our Project On Aspiration Based Agent Designs – Jobst Heitzig

SatisfIA – Updates From Our Project On Aspiration Based Agent Designs – Jobst Heitzig Horizon Omega

40 views - 2 years ago

ProgressAlign: Towards Moral Progress Algorithms Implementable in the Next GPT – Tianyi Alex Qiu

ProgressAlign: Towards Moral Progress Algorithms Implementable in the Next GPT – Tianyi Alex Qiu Horizon Omega

76 views - 2 years ago

Condor Global SEA: The case for building an AI Safety Hub in Southeast Asia – Lexley Maree Villasis

Condor Global SEA: The case for building an AI Safety Hub in Southeast Asia – Lexley Maree Villasis Horizon Omega

81 views - 2 years ago

Introduction to World State Graph Structure Analysis – Johannes C Mayer

Introduction to World State Graph Structure Analysis – Johannes C Mayer Horizon Omega

23 views - 2 years ago

AI Safety & Healthcare: What is Safe Medical AI – Rachel Draelos

AI Safety & Healthcare: What is Safe Medical AI – Rachel Draelos Horizon Omega

18 views - 2 years ago

Gaia: Planetary Scale AI Safety – Rafael Kaufmann

Gaia: Planetary Scale AI Safety – Rafael Kaufmann Horizon Omega

39 views - 2 years ago

Social Choice for AI Ethics and Safety: An Emerging Research Community – Jobst Heitzig

Social Choice for AI Ethics and Safety: An Emerging Research Community – Jobst Heitzig Horizon Omega

18 views - 2 years ago

Fundamental Controllability Limits – Remmelt Ellen

Fundamental Controllability Limits – Remmelt Ellen Horizon Omega

21 views - 2 years ago

Compute Governance as a Policy Lever for Effective AI Governance – Angshuman Kaushik

Compute Governance as a Policy Lever for Effective AI Governance – Angshuman Kaushik Horizon Omega

57 views - 2 years ago

Agentic AI Safety Guidelines – Nell Watson

Agentic AI Safety Guidelines – Nell Watson Horizon Omega

57 views - 2 years ago

Provably Safe AI – Steve Omohundro

Provably Safe AI – Steve Omohundro Horizon Omega

300 views - 2 years ago

AI Driven Labor Market Impacts and Economic Safety Nets – Arturs Kanepajs

AI Driven Labor Market Impacts and Economic Safety Nets – Arturs Kanepajs Horizon Omega

12 views - 2 years ago

Provably Safe AI – Steve Omohundro

Provably Safe AI – Steve Omohundro Horizon Omega

236 views - 2 years ago

Synthesizing Gatekeepers for Safe Reinforcement Learning by Justice Sefas

Synthesizing Gatekeepers for Safe Reinforcement Learning by Justice Sefas Horizon Omega

84 views - 2 years ago