Elo Clínico:

Phenomenological Fine-tuning for Medical AI Alignment

Reducing Risk in AI Safety Through Expanding Capacity.

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

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

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.

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

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

Alignment as epistemic system governance under compression

We reframe the alignment problem as the problem of governing meaning and intent when they cannot be fully expressed.

Course Buyouts to Work on AI Forecasting, Evals

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.

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

ExoPriors, Inc. founder runway

building foundational subjective judgement infrastructure

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