Offline AI for Empowering Underserved Teens (Pilot PoC)

A privacy-first SLM trained on 2,000+ real teen experiences, optimized to run without internet on low-end smartphones for accessible mental well-being

Offensive Cyber Kill Chain Benchmark for LLM Evaluation

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

Transluce: Fund Scalable Democratic Oversight of AI

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

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

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.

SOTA Public Research Database + Search Tool

Unlocking the paradigm of agents + SQL + compositional vector search

Addressing Agentic AI Risks Induced by System Level Misalignment

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

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

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

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

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

Elo Clínico:

Phenomenological Fine-tuning for Medical AI Alignment

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

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.

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

Building Frontier AI Governance Capacity in Africa (Pilot Phase)

A pilot to build policy and technical capacity for governing high-risk AI systems in Africa