Hardware support for underprivileged engineering students

Funding a laptop for first-year computer science engineering students who currently have no own pc

Beyond single-agent safety: Training LLM agents to cooperate

Reinforcement learning for cooperative LLM agents to address multi-agent risks.

Benchmarking Multimodal AI for Undiscovered Species Detection

How current fusion models perform under real-world signal degradation, not lab conditions.

US Policy Communication Playbook for an AI Crisis

A playbook to help AI safety policy advocates communicate with the U.S. government during the window of opportunity during an AI-related crisis.

Developing a Latin American analytical framework for AI

Support to complete a peer-reviewed paper applying a Latin American decolonial framework to artificial intelligence

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

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

AI Safety Nepal

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

Do Language-Model Process Reports Track Their Underlying Computation?

Testing an architectural explanation for tension–flow reports during recursive self-focus

Originality, Quantification, and Decomposition of Generalization.

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

[Test] new grant signature flow

testing one two three

TARP - The Answer to Roadside Pens

An Intervention Towards Animals Under Extreme Heat Stress

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.

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.

Evaluating framing effects on LLM refusal during compositional task interference

Pax Machina

A publication about the institutions we need for powerful AI.

Tracking Mindless AI Usage Through Digital Biometrics

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

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

Building LemmaScript, a verification toolchain for TypeScript

Travel grant to attend HAAISS Prague 2026

Emotion as Attack Surface and Monitoring Signal in Thinking Models