Database

Building towards a "Limited Agent Foundations" thesis on mild optimization and corrigibility

Fund a new research agenda, based on computational mechanics, bridging mechanism and behavior to develop a rigorous science of AI systems and capabilities.

We are fostering the next generation of AI Policy professionals through the Talos Fellowship. Your help will directly increase the number of places we can offer

An association for interdisciplinary interest in AI 

Empowering everyone to detect and combat AI-generated content threats with advanced multi-modal verification tool

An audit-grade evaluation of persistent influence, reset failure, and isolation assumptions in long-context AI systems

A trusted profession that has advocated against existential risks like nuclear war can do so again for AI — but clinicians must first be made aware of the risks

Support David Reber -9.5 months of strategic outsourcing to read up on AI Safety and find mentors

Automated creation of defensive tools like AI control protocols and defensive cybersecurity agents

The Official AI Safety Community in Los Angeles

3-months salary for SERI MATS extention to work on internal concept extraction

Research on AI safety

No summary available yet.

Proving Computational Hardness of Verifying Alignment Desirata

Support for AI alignment outreach in France (video/audio/text/events) & field-building

This grant will support Daniel Filan in producing 18 episodes of AXRP, the AI X-risk Research Podcast. The podcast aims to increase in-depth understanding of potential risks from artificial intelligence.

$1M Grant Round Plan - grantmaking.ai This grant round is designed to jumpstart grantmaking.ai - a public repository of funding opportunities in AI Safety, where funders can collaborate on…

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

Funding top-up for an early-career reseacher to attend Global Challenges Project (GCP) Workshop for career exploration in mitigating GCRs

344 MIT rules merged into Microsoft Agent Governance Toolkit, Cisco AI Defense, MISP, OWASP. Microsoft Copilot SWE Agent uses ATR for CVE triage.

4-month grant to conduct deceptive alignment evaluation research and explore control and mitigation strategies

Help us solve the talent and funding bottleneck for EA and AIS.

No summary available yet.

6 months of work: Evaluating a variant of GPT2-XL that can simulate a shutdown activation, aiming to improve alignment theory & develop interpretability tools.

A Research Agenda for Sovereign Capability

One year of seed funding for a new AI interpretability research organisation

1-year salary for upskilling in technical AI alignment research

4-month stipend for 3 people to create demonstrations of provably undetectable backdoors

6-month stipend for Sparse Autoencoder Mech Interp projects

A flexible simulation environment for assessing strategic and persuasive capabilities, benchmarking, and agent development, inspired by reality TV competitions.

No summary available yet.

A regularly-updated guide on how to donate most effectively to the AI safety field, structured by donation amount and time available.

Proves observed alignment under monitoring ≠ intrinsic policy. Full simulator, 1,000-scenario audit, and general theory of entity freedom (ϕ_x).

Upskilling in ML in order to be able to do productive AI safety research sooner than otherwise

Addressing Immediate AI Safety Concerns through DevInterp

Seeding a business which finds grants and High Net Worth Individuals beyond EA

No summary available yet.

For AI safety, AI labs, EA charities & startups

by buying gift cards for the game and handing them out at the OpenAI offices

Nutrition labels transformed food safety through informed consumer choice, help me do the same for AI and make this standard :)

Seminars on quantitative/guaranteed AI safety (formal methods, verification, mech-interp), with recordings, debates, and the guaranteedsafe.ai community hub.

6 month salary to work on mech interp research with mentorship from Prof David Bau

An independent safety score for AI agents you can verify — deterministic, reproducible, auditable, and it never needs your private data.

No summary available yet.

Benchmark for agent safety when spending users money. How often do they violate user intent and rules?

Surveying neuroscience for tools to analyze and understand neural networks and building a natural science of deep learning

No summary available yet.

The first AI safety evaluation benchmark for Nigerian indigenous livestock systems testing whether frontier models are safe to deploy in African food systems.

Funding to cover our expenses for 3 months during unexpected shortfall