Guaranteed Safe AI Seminars 2026

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

AI-Powered Knowledge Management System for Alignment Research

Funding to cover the first 4 month and relocating to San Francisco

Enabling a Student to Present his Mechanistic Interpretability Work at NeurIPS

Help fund our student’s trip to NeurIPS to present his main conference paper on interpretable features in text-to-image diffusion models.

Tech-Powered Database Platform for Traceability and Deforestation Monitoring.

Funding to integrate AI satellite monitoring tools, Google GPS, Cloud-based storage software, AI-assisted geospatial analysis and real-time analytic report.

Travel grant to attend San Diego Alignment Workshop and NeurIPS

Attending NeurIPS and the San Diego AI Alignment Workshop to advance research on neural network safety and complexity.

Fund a Fellow for the Cooperative AI Research Fellowship!

A 3-month fellowship in Cape Town, connecting a global cohort of talent to top mentors at MIT, Oxford, CMU, and Google DeepMind

Finishing a Video on the Google DeepMind Hunger Strike

Funding gap to pay for a video editor and scriptwriter

Synthesizing Standalone World-Models

Research agenda aimed at developing methods for constructing powerful, easily interpretable world-models.

Travel Funding to present research at NeurIPS 2025

A self-funded researcher presenting at NeurIPS NeurReps to showcase a new approach to geometry and cognition.

AI scam research targeting seniors

A microgrant to help us scale our research on AI-assisted online scams by building real-world defenses for seniors and collecting data for ScamBench.

Groundless Alignment Residency 2025

Practicing Embodied Protocols that work with Live Interfaces

TransformerLens - Bridge Funding

Responsible AI Governance Initiative (RAI-GI)

Elevating Africa’s Missing Voice in Global AI Safety

Generate and share music about AI risk

I am making music about AI risk

'Making God': a Documentary on AI Risks for the Public

Geoffrey Hinton & Yoshua Bengio Interviews Secured, Funding Still Needed

Orexin Pilot Experiment for Reducing Sleep Need

Testing intranasal orexin-A administration for sleep need reduction: a 2-3 participant self-blinded randomized controlled trial

AI scam research targeting seniors

A microgrant to help us disseminate our work on AI scams targeting seniors and present it at BSides Las Vegas, DEF CON, and other conferences

Out of This Box: AI Safety Musical

Out of This Box: The Last Musical (Written by Humans)

Drive Narrative Change To Reduce Global Catastrophic Risk: Reach 1.3M people

Original essays, videos on systemic alternatives to shift the Overton window, build cultural momentum for policies supporting long-term resilience & well-being

Amplifying AI extinction risk awareness before it’s too late

Support our mission to educate millions through podcasts and videos before unsafe AI development outruns human control.