AI Safety Nepal

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

Music-based Human Autonomy Detector for Companion AI Users

Detecting AI Overreliance During Use of Chatbot Interfaces Through Symptoms

Through human behavioral symptoms when using AI chatbot interfaces, we can detect when the user is becoming overdependent, intervening and letting the user know

Synapse: Student Research Incubator

Expanding research access in LAUSD for underserved high school students.

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.

Rewind: Atomic Rollback Infrastructure for AI Agents

Ctrl+Z for AI agents. Rewind automatically snapshots the filesystem and the conversation together, so when your agent breaks something, one rollback fixes both.

Emotion as Attack Surface and Monitoring Signal in Thinking Models

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

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.

Travel grant to attend HAAISS Prague 2026

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.

PayBench: A Benchmark for Unsafe Commercial Autonomy

Benchmarking for AI safety when spending human money.

Making Secure, Local AI Agents to Investigate Cybercrime, Sex Crime, etc.

Local AI agents that help agencies analyze data and be compliant with data protocols, all while investigating cybercrime to sex offender violations.

Stress-testing alignment auditing methods of AuditBench

ICML Workshop Travel: Cross-Constitution Drift in LLM Character Training

Accepted ICML 2026 workshop paper on cross-constitution drift in LLMs; seeking $2,050 travel support to present in Seoul and gather research feedback.

Φ-Arena and adversarial multi-agent VLA interpretability

Independent collective. Φ-Arena open benchmark, 3 ICLR 2027 papers (Φ-Arena, mechinterp, energy-bounded) — kickstart for a 10-year program.

AI Safety Workshops For 6th-8th Graders in India

Inspiring India’s Middle‑Schoolers to pursue AI Safety, Governance, and X‑Risk Work

Machine God (documentary film)

Awareness-conditioned emergent misalignment

Does harmful fine-tuning data cause broad misalignment only when the model already recognises the target behaviour as a norm violation?