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.

AI Security Startup Accelerator Batch #2

Funding 5–10 AI security startups through Seldon’s second SF cohort.

Evaluating Model Attack Selection and Offensive Cyber Horizons

Measuring attack selection as an emergent capability, and extending offensive cyber time horizons to newer models and benchmarks

ExoPriors, Inc. founder runway

building foundational subjective judgement infrastructure

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.

Course Buyouts to Work on AI Forecasting, Evals

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.

Visa fee support for Australian researcher to join a fellowship with Anthropic

CaML - AGI alignment to nonhumans

Training AI to generalize compassion for all sentient beings using pretraining-style interventions as a more robust alternative to instruction tuning

Operating Capital for AI Safety Evaluation Infrastructure

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

SDCPNs for AI Safety

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

Disentangling Political Bias from Epistemic Integrity in AI Systems

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

Train LLMs in honest introspection

Train LLMs to accurately & honestly report on their internal decision-making processes through real-time introspection

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.

Inspect Evals

Funding to cover our expenses for 3 months during unexpected shortfall

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