Frozen white-box monitors for manipulation persistence in LLMs

Reproducible detector that reads whether a manipulation is still active in an LLMs stream. xfers across 6 model families.

programmatic internet search

scry.io, epistemic infrastructure for existential security philanthropy

Prediction of Inoculation Prompt Side Effects

An open, cheap method that detects when an inoculation prompt inoculates against off-target traits, so labs and developers can catch undesired trait/persona cha

Catching Fooled AI Judges: The Correspondence Auditor v3

Published. Validated on 1,200 cases (97.9–99.5%). The reasoning layer has a bug - we proved the fix works. $9,800 / 90 days to ship the open-source toolkit.

safely.bio: Customer screening for DNA synthesis providers

Deploying customer screening software at DNA synthesis providers to reduce AI-enabled biothreats

CryptoMind: Verifiable Safety for Financial AI Agents

An AI platform for crypto and stock analysis, news verification, scam detection and wallet safety, with an open-source Safety Kernel tested on TON.

Solving the memory issue in AI

Persistent memory in AI using LoRAs

Exploring Dynamic Constraint Boundaries for Auditable AI

Testing whether dynamic boundaries, history, feedback, and uncertainty-aware decisions can make AI behavior more interpretable and auditable.

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.

Trace Continuity: Making AI Prove It Still Has Authority

Testing whether AI can be governed at the moment it acts, then putting that protection to work for organizations that need it most.

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

Nipping AI-Fabricated Science Claims in the Bud

Agent Roles, a Constitution and Governance in the Research Workflow

AI Safety Nepal

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

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

AI Safety Museum - Berlin Pilot

Increasing public awareness of AI risks and benefits through in-person, interactive experiences

Himalayan Peak Finder

An offline mobile app that uses location, elevation, and computer vision to identify Nepal’s mountains and help people explore, capture, and learn about them.

What Happens If We Actually Test It?

Independent Behavioral Research on Open-Weight AI Models

Auditable scientific debate reconstruction, AI for Science

AISafety, AI and Science, AI for Human Reasoning

Reverse Engineering LLM Alignment

TRiADiC Intelligence Labs ethical alignment research program and consumer empowerment educational program.

Originality, Quantification, and Decomposition of Generalization.

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