Safeguarding DNA Synthesis from Biological Risks Posed by Advanced AI

We will test whether circuits in protein language models can detect function-preserving redesigns of known toxins that evade homology-based DNA-synthesis screen

TARP - The Answer to Roadside Pens

An Intervention Towards Animals Under Extreme Heat Stress

Supplementing Summer Program for Applied Rationality and Cognition 2026 (SPARC)

[Test] new grant signature flow

testing one two three

AI Safety Nepal

Five-week AI safety fellowship + 3-month project mentorship

Anthropology of Machines: Mechanistic Interpretability for Social Sciences

A hands-on book teaching social scientists to observe, intervene on, and validate what happens inside a language model.

Originality, Quantification, and Decomposition of Generalization.

Perform research to rigorously elucidate and quantify generalization versus memorization, and examine evidence of originality in LLMS.

Evaluating framing effects on LLM refusal during compositional task interference

KernelBench: an independent benchmark for AI-automated GPU kernel engineering

Frontier-model sweeps, hardware-roofline scoring, and reward-hacking audits at kernelbench.com. Keeping an independent AI R&D automation benchmark alive.

Tracking Mindless AI Usage Through Digital Biometrics

Analyzing user behavior patterns in chatbot interfaces to detect real-time symptoms of AI overdependence

Silicon anode validation for Li-ion batteries

Funding external tests to see if a silicon-anode pathway can improve Li-ion energy density while staying compatible with existing manufacturing

Pax Machina

A publication about the institutions we need for powerful AI.

Making sure that the code AI pushes to the internet is safe and bug-free

Building LemmaScript, a verification toolchain for TypeScript

Emotion as Attack Surface and Monitoring Signal in Thinking Models

Travel grant to attend HAAISS Prague 2026

Finding and Defending the Attention Circuits That Make LLMs Jailbreakable

Mapping the attention heads that push LLMs toward refusal vs. compliance, and building an inference-time defense against both single- and multi-turn jailbreaks.

Publishing Generation Z: Redefining Work, Success and the Digital Future

An open-science monograph with (1) a signed Letter of Intent from Anthem Press and (1) empirical research on compiled, harmonised open-access dataset

AI Safety Roster: a searchable directory of everyone in AI safety

A fast, comprehensive directory of the people and orgs in AI safety: search, filter, and match.

Synapse: Student Research Incubator

Expanding research access in LAUSD for underserved high school students.

PayBench: A Benchmark for Unsafe Commercial Autonomy

Benchmarking for AI safety when spending human money.