APCs for Comp. Bio Papers in Review - Independent Researcher

"ICML published ML researcher — evaluation validity, mechanistic interpretability applied to biology

Simulation to reality Robotics Gap

Testing when VLA world models (Robots) simulation doesn't matchs the reality before it becomes an incidents

GharBench - Benchmark of LLM sales agents under Indian law (WhatsApp, Hinglish)

First benchmark of AI sales agents under RERA and consumer-protection constraint: compliance hard-fails zero the score, human-validated LLM judges, 50% Hinglish

programmatic internet search for expansive curiosity

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

Second World

Fund travel support to a music-AI hackathon & creative tech building 

Support for a team of four & narrative rap about technological change

Senses for Embodied Robotics: Tactile pressure - third sense

Tactile sensing for a robotic body with audio, visuals, and cooling systems - prototyping the sensor array for third android sense.

FloraForge: Building a Reusable Genetic Platform for New Flower Traits

CoastGuard AI - Monitoring Coastal Erosion with Satellite Data and AI

Comparing decades of satellite imagery to predict and pevent coastal loss, starting in Greece

AI Safety Museum - Berlin Pilot

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

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.

The public record of AI model change

AI companies change the models behind the names you build on. Sometimes they say so. Sometimes they do not. Either way we write it down.

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.

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

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.

AI Safety Nepal

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

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

Catching Fooled AI Judges: Open-Source Verification for AI Pipelines

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