11th edition of AI Safety Camp

Cost-efficiently support new careers and new organisations in AI Safety.

SafePlanBench: evaluating a Guaranteed Safe AI Approach for LLM-based Agents

Seeking funding to develop and evaluate a new benchmark for systematically assesing safety of LLM-based agents

Unprompted Unfaithful Chain of Thought Dataset Project

Legislative and Policy Innovations for Safer Medical Device Recalls

with a Focus on Neurosurgery and Software as a Medical Device (SaMD)

LLM Approximation to Pass@K

Pilot for new benchmark by Epoch AI

For tracking and predicting future AI progress to AGI

Act I: Exploring emergent behavior from multi-AI, multi-human interaction

Community exploring and predicting potential risks and opportunities arising from a future that involves many independently controlled AI systems

Finishing The SB-1047 Documentary

How California became ground zero in the global debate over who gets to shape humanity's most powerful technology

Web Documentary: Local Insights on AI Safety for Sub-Saharan Communities.

Mechanistic Interpretability research for unfaithful chain-of-thought (1 month)

Iván and Jett are seeking funding to research unfaithful chain-of-thought, under Arthur Conmy's mentorship, for a month before the start of MATS.

AI safety fieldbuilding in Warsaw, Poland (funding for 1 semester)

Reach the university that trained close to 20% of OpenAI early employees

MoSSAIC

Probing possible limitations and assumptions of interpretability | Articulating evasive risk phenomena arising from adaptive and self modifying AI

80,000 Hours

We provide research and support to help people move into careers that effectively tackle the world’s most pressing problems.

Lightcone Infrastructure

Funding for LessWrong.com, the AI Alignment Forum, Lighthaven and other Lightcone Projects

More Detailed Cyber Kill Chain For AI Control Evaluation

Extending an AI control evaluation to include vulnerability discovery, weaponization, and payload creation

Horizon Events 2025

Non-profit facilitating progress in AI safety R&D through events

Shallow review of cost-effectivness of technical AI safety orgs

Do ACE-style cost-effectivness analysis of technical AI safety orgs.

Arkose

AI safety outreach to experienced machine learning professionals

Coalition for a Baruch Plan for AI

Catalyzing a uniquely bold, timely and effective treaty-making process for AI

AI Safety & Security workshop with Adversarial Simulation labs

Workshop focused on AI Security attacks and defense use-cases through a Capture-the-flag style Adversarial simulation labs.