Solving the memory issue in AI

Persistent memory in AI using LoRAs

Toward a Superhuman, Open-Ended Alignment Auditor

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

AI Safety Hong Kong (AISHK)

Surrogate base model for Mechanistic Interpretability

Creating a reference model for mechanistic interpretability without assuming that at auditing time we have a safe model to compare the suspicious model against.

Sentient Futures Project Incubator

Funding compute/API costs for Incubator projects that build nonhuman welfare consideration into AI safety work

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.

Agent limits that survive delegation

When an AI agent spawns sub-agents, its safety limits do not follow. I build and deploy the layer that makes them inherited and non-strippable.

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.

Nipping AI-Fabricated Science Claims in the Bud

Agent Roles, a Constitution and Governance in the Research Workflow

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.

The AI Safety Stack

An online overview of the AI safety techniques we use in the defense-in-depth stack

What Happens If We Actually Test It?

Independent Behavioral Research on Open-Weight AI Models

Auditable claim extraction and comparison of claims across scientific literature

AISafety, AI and Science, AI for Human Reasoning

Artificial Selves

Integrating Selves and Research on Selves in the AI Community

Evaluating the safety, ethics, and values of quantized and finetuned open models

Help me evaluate the safety, ethics, and values of the quantized and fine-tuned open-weight LLMs that individuals and enterprises are actually using.

Belief state geometry of language model personas

A formal, testable account of LLM persona selection as Bayesian inference, validated with model internals, so labs can monitor and steer personas.

AI safety for builders hackathon / fellowship

AI safety for builder hackathon / fellowship - to build tools, products, etc.

Travel Grant to Present My Mechanistic Interpretability Research at MICCAI 2026

Help an undergraduate mechanistic interpretability researcher present accepted AI-safety work at Mechanistic Interpretability workshop of Medical model 2026.

Getting Split-Personality Training ready for deployment

Clearing barrieers to adoption for an existing ICML-published interpretability technique that can elicit latent knowledge from red teamed model organisms