Alexander Turner
NTU AI Safety
Henry Castillo
Samuel Ratnam
An interdisciplinary research group based in Oxford for character training, model pyschology and multi-agent interaction dynamics
Pradeep
A reward model that scores answers on 6 quality dimensions, built on 7,500 pairs and free GPUs. Seeking funds to scale it.
Ruth Seleo
Research relevant for (suffering focused-) AI Alignment
Chanderprakash Sharma
Xiaocong Yang
AISA
APEC, Bangkok 2026
Habeeb Abdulfatah
Accepted poster at the Global South AI event. Registration is paid; Require funding for flight and accomodation.
Space Lutterodt-Clottey
Producing a Digital Circus-Esque animated series aimed to give a semi-realistic didactic shot at teaching what superintelligent ruin looks like
Mohamed Aly
NeurIPS is paying my hotel and registration. I need the flight to present the papers.
Lawrence Wagner
Andrew Kemeklis
Train a 7B model on 1T constrained tokens (commonsense reasoning, in-context learning, instruction following, and safe everyday tasks).
Attila Tóth
The Arena is a world, a framework in which AI agents can experience existence. We humans can learn from it: what makes us more?
Madhav Khanal
Accepted oral and poster at ACML 2026, 1 to 4 December. School funded registration and visa cost; flight from US to Australia and lodging remain on me.
Jaeson Booker
A testbed for hundreds of alignment/interp papers.
Creating a Stronger Pipeline into Technical AI Safety Research
Constance Li
Animal Welfare Midtraining Data Creation
Maximilian Kornstein
A test of frontier model’s tipping point regarding saving human lives and animal lives, or obeying human orders. It is a test or alignment and morals.