Boundary-Mediated Models of LLM Hallucination and Alignment

A mechanistic, testable framework explaining LLM failure modes via boundary writes and attractor dynamics

Protocol-Level Interaction Risk Assessment and Mitigation (UIVP)

A bounded protocol audit and implementation-ready mitigation for intent ambiguity and escalation in deployed LLM systems.

TimeAlign v2: contamination-aware evals for small models (16GB GPUs)

Reusable, low-compute benchmarking that detects data leakage, outputs “contamination cards,” and improves calibration reporting.

From Nobel Signatures to Binding Red Lines: The 2026 Diplomatic Sprint

Leveraging 12 Nobel signatories to harmonize lab safety thresholds and secure an international agreement during the 2026 diplomatic window.

Formal Certification Technologies for AI Safety

Developing the software infrastructure to make AI systems safe, with formal guarantees

Runway till January: Amplify's funding ask to market EA & AI Safety 

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

Retroactive: Presenting a poster at the ICML technical AI governance workshop

Operating Capital for AI Safety Evaluation Infrastructure

Enabling rapid deployment of specialized engineering teams for critical AI safety evaluation projects worldwide

Disentangling Political Bias from Epistemic Integrity in AI Systems

An Integrative Framework for Auditing Political Preferences and Truth-Seeking in AI Systems

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.

The Deal of the Century (for AI)

Persuading a critical mass of key potential influencers of Trump's AI policy to champion a bold, timely and proper US-China-led global AI treaty

Inspect Evals

Funding to cover our expenses for 3 months during unexpected shortfall

How to mobilize people on AI risk: experimental message testing

Experimental message testing and historical analysis of tech movements to identify how to effectively mobilize people around AI safety and governance

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

6 Month Stipend to Support a Transition to AI Governance Work

Funding research on how AI hype cycles can drive unsafe AI development

When Safety Testing Costs More Than Model Training

Multi-agent AI security testing that reduces evaluation costs by 10-20x without sacrificing detection quality

Tarbell Center for AI Journalism

$200k in 1:1 matched funding to support reporting on AI.

Finishing a Video on the Google DeepMind Hunger Strike

Funding gap to pay for a video editor and scriptwriter

Grow An AI Safety Tiktok Channel To Reach Ten Million People

20 Weeks Salary to reach a neglected audience of 10M viewers

Global Governance & Safety Layer for Advanced AI Systems - We Stop Rogue AI

Building the first external oversight and containment framework + high-rigor attack/defense benchmarks to reduce catastrophic AI risk.