Krishan Kumar Verma
I found agents that never once said they couldn't do the job. And two models that swap places depending on which job you give them.
Muhammad
An open-source study of AI safety, dialect accuracy, and hallucination in farming contexts.
Abeer Sharma
Nikhil Maturi
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
Constance Li
Funding compute/API costs for Incubator projects that build nonhuman welfare consideration into AI safety work
IBBIS
Defining which sequences are dangerous enough to screen for, so providers and regulators screen consistently
Giorgos Tsimpoulis
Comparing decades of satellite imagery to predict and pevent coastal loss, starting in Greece
Cecil Abungu
A junior research fellowship for recent African graduates that combines ILINA’s spring seminar with a mentored research phase on AI and global catastrophic risk
William Wu
Hosting a full day conference based in Sydney, Australia where young, aspiring students in senior high school and university interested in AI Safety can connect
Genevieve Shea
A practical evaluation framework to identify governance failures in frontier AI systems during elections.
Next year of Commec (the Common Mechanism), the free, open-source, globally-available DNA synthesis screening tool hosted by IBBIS
Phil Palmer
Deploying customer screening software at DNA synthesis providers to reduce AI-enabled biothreats
Sofia Yablonskaya
Monthly analysis of China's algorithm-filing registry and binding AI security standards, read in Chinese, for the people calibrating AI rules in the West.
Jai Dhyani
Creating conditions for cooperative strategies to dominate adversarial ones among near-future AIs while we still can
Eitan Sprejer
The Argentinian AI Safety community (BAISH, baish.com.ar) is the largest in Latin-America. Support BAISH's growth, by providing funding for paying salaries.
Gabriel Sherman
A playbook to help AI safety policy advocates communicate with the U.S. government during the window of opportunity during an AI-related crisis.
Pip Foweraker
A nightmarishly hard AI safety strategy game about holding p(Doom) down. You can't win; you can only buy time.
David Yu
Agwu Naomi Nneoma
Developing practical, plain language AI oversight framework that an organisation can easily adopt regardless of regulatory capacity.
Mekaoui Helmy
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.
