Paper Clip Apocalypse (War Horse Machine)

Short Documentary and Music Video

Terminal Boundary Systems and the Limits of Self-Explanation

Formalizing the "Safety Ceiling": An Agda-Verified Impossibility Theorem for AI Alignment

Learn & Launch: Monthly Training and Mentorship for Early-Stage AI Safety & Gov.

A low-cost, high-leverage capacity-building program for early-career AI safety and governance practitioners

Transluce: Fund Scalable Democratic Oversight of AI

Technical Implementation of the Tiered Invariants AI Governance Architecture

Achieving major reductions in code complexity and compute overhead while improving transparency and reducing deceptive model behavior

Isolating CBRN Knowledge in LLMs for Safety - Phase 2 (Research)

Expanding proven isolation techniques to high-risk capability domains in Mixture of Expert models

Reducing Risk in AI Safety Through Expanding Capacity.

Offensive Cyber Kill Chain Benchmark for LLM Evaluation

Measuring whether AI can autonomously execute multi-stage cyberattacks to inform deployment decisions at frontier labs

AI Security Startup Accelerator Batch #2

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

Addressing Agentic AI Risks Induced by System Level Misalignment

AI Safety Camp 2026 project: Bidirectional Failure modes between security and safety

Architectural Governance to Prevent Authority Drift in AI Systems

A constraint-first approach to ensuring non-authoritative, fail-closed behavior in large language models under ambiguity and real-world pressure

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

AURA Protocol: Measurable Alignment for Autonomous AI Systems

An open-source framework for detecting and correcting agentic drift using formal metrics and internal control kernels

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.

SOTA Public Research Database + Search Tool

Unlocking the paradigm of agents + SQL + compositional vector search

Shallow Review of AI Governance: Mapping the Technical–Policy Implementation Gap

Identifying operational bottlenecks and cruxes between alignment proposals and executable governance.

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