AI safety projects actively seeking funding: what they’re working on and how much they need.
Showing 51-100 of 111 Top rated
A non-LLM graph neural network compares code property graphs with trusted references to detect backdoors at low false-positive rates and provide node-level audit trails. Read more
SpecCheck detects intent drift in LLM-formalized requirements using ambiguity elicitation and cross-model validation, evaluated on Lean 4 theorems and Python property-based tests. Read more
The project evaluates secret-loyalty detections with matched controls and finds prior signals spurious, while verifying that organism C is byte-identical to the base model. Read more
Develops an internal-representation scanning tool to detect hidden loyalties in AI models by comparing entity representations, and critiques existing sleeper-agent benchmarks. Read more
An open-source multilingual safety benchmark evaluates Llama models across South and Southeast Asian languages, revealing under- and over-refusal caused by English-centric safety training. Read more
An independent Australian podcast raising public and policymaker understanding of catastrophic risks from transformative AI — hosted by an ethicist and an AI-governance practitioner in an under-served region for AI safety. Read more
How do you map your old concepts to new concepts when your model of the world gets updated? How would you translate concepts you care about to new ontology? I plan to adress this via extending "Condensation: Theory of Concepts" - Eisenstat, (2025) Read more
Testing whether the safety circuits in language models actually work in Igbo (Nigerian Language) and building evaluations that distinguish real refusals from accidental ones. Read more
consolidate, extend, and manually validate an AI-alignment field map, close gaps, perform backtests, post Metaculus questions, and write LessWrong posts about the map. Read more
Expand "Humanity Tomorrow" website with a multilingual AI Risks & Mitigations Map connecting risks, causal pathways, mitigation strategies, remaining gaps, and project ideas, while maintaining the existing AI Risks FAQ. Read more
Machine-verified core (190 Lean 4 modules, 0 sorryAx) and GRPO-aligned model achieving +15.6% accuracy with a 37.2% reduction in reasoning tokens. Read more
An open observatory of the data behind the AI buildout: which public records show where data centers and the power systems around them are, how open and checkable those records are, and what is still missing. Read more
We will test whether AI assistance that performs developing cognitive operations weakens adolescents’ later independent judgment, and develop evidence-based safeguards that keep human reasoning meaningfully in the loop. Read more
4 open funding asks
A two-phase study of context-induced persona-pattern uptake: first establishing reproducible behavioral contrasts and boundary conditions, then testing what mechanistic signatures distinguish those states and whether candidate mechanisms can be causally manipulated. Read more
Establishing Nepal's biotechnology research infrastructure to develop genomic solutions for climate-resilient agriculture, strengthen food security, and advance locally led scientific innovation. Read more
Consumer Awareness Platform for AI Risks Read more
A pilot curriculum of six Socratic seminars for educators and other nontechnical learners. Read more
Testing whether AI agents can comply with corrective instructions after their earlier actions have already reduced or eliminated effective human control. Read more
Travel support for an independent researcher from Bangladesh to present his single-author NeurIPS 2026 paper on how efficiently LLMs reason. Read more
A model-agnostic method and tool for independently testing whether advanced AI systems remain stable and appropriately corrigible without requiring access to model internals. Read more
Independently replicate and open-source a model-free AI agent monitor that caught 209 of 210 sabotage runs, plus static checks that find fail-open defects in safety tooling. Read more
The Universal Stability Criterion (USG) project establishes a domain‑agnostic protocol that anticipates collapse in symbolic complex systems by detecting structural deviation before failure.… Read more
The GRACE (Governed Release Architecture for Critical Environments) protocol establishes a six‑layer governance matrix that embeds stability and safety checks directly into the release pipeline of… Read more
PGVP is a simple diagnostic protocol that reliably distinguishes true periodic generalization from spurious curve fitting, ensuring models are structurally validated before deployment. Read more
Planned Malawi-registered nonprofit building Southern Africa’s AI safety capacity via global/local fellowships, institutional placements with expert mentoring, and regional AI safety research, starting with a Malawi pilot. Read more
Supporting research on when LLM-guided optimisation systems fail under changing specifications, constraints, and environments. Read more
I am requesting $5,160 to present my first-author NeurIPS paper on phase transitions in attention and their implications for predicting and monitoring emergent capabilities. Read more
Measuring what it costs to expose model activations for safety probes in vLLM and SGLang, and making that access standard for anyone serving open models. Read more
Open-source AI Agent key bound delegatable and revocable authorization framework extending GNAP, an IETF standard. Read more
GAIOS is an AI platform with modular tools for agriculture, health, education, energy and governance in Cameroon, initially building and piloting RIN AGRIC and RIN MEDIC with local users in Bamenda. Read more
Autotelic agents that contribute to the global economy like people. Read more
Building Hispanic participation in advanced AI safety and helping Hispanic-serving institutions advocate for effective AI governance. Read more
TRIAD AI proves that balanced, supervised fine-tuning aligns large language models without this use of reinforcement learning pipelines, eliminating the prescriptive bias that harms vulnerable users in human-service settings. Read more
2 open funding asks
Personalised medicine platform with intelligence to improve cancer patient's treatment outcomes with improved survival rate Read more
A scalable fellowship training researchers to develop interventions for achieving high-value long-term futures Read more
Producing a Digital Circus-Esque animated series aimed to give a semi-realistic didactic shot at teaching what superintelligent ruin looks like Read more
AIs keep going wild on the web, what are they up to? Read more
Which actors gain relative power under different interventions, and what are the expected consequences? Read more
How much information can a language model transmit through a constrained channel? We’re testing this in our first E3-A experiment. Read more
Funds BASE Research’s executive team travel to EA Global NYC 2026 to meet funders/partners and advance biosecurity programs, fellowship development, and AI governance/evaluation collaborations. Read more
APEC, Bangkok 2026 Read more
An open-source, model-agnostic governance layer that uses constitutional state, trajectory memory, and mathematical control mechanisms to govern LLM and AI-agent behavior at runtime. Read more
I borrowed from friends for two years to transition into AI governance research. It worked. Now I need the debts cleared so I can work in peace. Read more
Requesting $750 to fund travel, lodging, and expenses for an AI Safety Nepal representative to attend Swiss AI Safety Days 2026 in Zurich to network and learn field-building practices. Read more
Ensuring our ability to grow in a sustainable manner Read more
An interdisciplinary research group based in Oxford for character training, model pyschology and multi-agent interaction dynamics Read more
Flights and visa sponsorship for a first-time presenter from India, sharing research on whether LLMs behave differently when they think they are being tested. Read more
PauseAI Canada organizes media outreach, public events and grassroots advocacy to secure Canadian support for an international treaty pausing frontier AI training. Read more
Funds Parveen Sheikh to travel from India to present an AI safety governance poster at Swiss AI Safety Days and attend EAGxBerlin for networking and collaborations. Read more
Produce a 4-episode technical AI alignment podcast interviewing researchers about their agendas, funding equipment, travel/space, and the host’s time. Read more
