Database

Advocating for U.S. federal AI safety legislation to reduce catastrophic AI risk.

12 month stipend and expenses to research in AI Safety (Unlearning; Modularity; Probing Long-term behaviour)

I've self funded my ramp up for six months and interview/grant processes are taking longer than expected.

Cover participant stipends for AI Safety Camp Virtual 2023

6-months of part-time stipend to launch a new science journalism outlet focused on AI Safety

Promoting better management of Global Catastrophic Risks in Spanish-Speaking countries.

No summary available yet.

No summary available yet.

Unlearning, AI Safety

Organizing global AI ethics think tank for dynamic AI research updates and framework for AI safety policies implementation and humanity income support

This grant is funding a 6-month stipend for Bilal Chughtai to work on a mechanistic interpretability project

12 week 0.6FT upskilling stipend for technical governance research management

PhD in Computer Science working on AI-safety

Mapping the attention heads that push LLMs toward refusal vs. compliance, and building an inference-time defense against both single- and multi-turn jailbreaks.

Stipend for a master’s thesis and paper on technical alignment research: mechanistic interpretability of attention

Updates, additional resources and promotion for a 4-week introductory syllabus that looks at interventions to help prevent future pandemics.

Running the initial online version of a 4-week biosecurity course for 20-50 participants

6 month AI alignment internship stipend top-up

LLMs often know when they are being evaluated. We’ll do a study comparing various methods to measure and monitor this capability.

Social media content across YouTube, Instagram, and TikTok to grow AI x-risk awareness and build political momentum for a global pause.

Inspiring India’s Middle‑Schoolers to pursue AI Safety, Governance, and X‑Risk Work

4-month stipend to research the mechanisms of refusal in chat LLMs

6-month salary and compute budget for continuing work on mechanistic interpretability for attention layers

6-months salary for researching “Framing computational systems such that we can find meaningful concepts." & Upskilling

No summary available yet.

SFF main round did us dirty!

Developing an innovative wisdom layer for AI that enhances its capabilities for deep analysis, safe AI, and creative solutions to complex systemic problems.

This grant is funding a $35,000 stipend plus $10,000 in compute costs for Yuxiao Li's independent inference-based AI interpretability research.

~4 FTE for 9 months to fund WhiteBox Research, mainly for the 2nd cohort of our AI Interpretability Fellowship in Manila

3-month funding for upskilling in technical AI Safety to test personal fit and potentially move to a career in alignment

De-risking AI Catastrophe: A cyber-physical protocol using ZKPs and NIR Spectroscopy to resolve the governance deadlock in critical global infrastructure.

6 months salary to do independent AI alignment research focused on formal alignment and agent foundations

Developing correct-by-construction world models for verification of frontier AI

Surveying experts on AI risk scenarios and working on other projects related to AI safety.

No summary available yet.

6-month salary to build & enhance open-source mechanistic interpretability tooling for AI safety researchers

4-6 month salary to do circuit-based mech interp on Mamba, as part of the MATS extension program

Grant to cover fees for a master's program in machine learning

6 month salary & operational expenses to start a cybersecurity & alignment risk assessment org

We build a scalable "Automated Circuit Discovery" method and investigate "Cleanup Behavior" to advance the interpretability of transformer models.

6-month funding for a team of researchers to assess a novel AI alignment research agenda that studies how structure forms in neural networks

Part-time salary for independent AI safety research

Measured post-embodied sensation integration. Solo daily-pace brain-function development in Osaka. Phase 1 funds higher cognitive integration program.

1-year salary for research in applications of natural abstraction

Triadic geometric training data and architecture replaces RLHF

Six-month support for a Program Manager to organize and execute international AI safety hackathons with Apart Research

General support of research led by John Wentworth

4-month salary to work on a project finding the most interpretable directions in gpt2-small's early residual stream

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