Nullius
Team?
Project
Database
The AI Safety database is a work in progress, as we are focusing on the launch of the initial $1M grant round. Feel free to send us ideas or feedback!
| Name | Type | Tags | Endorsed | Team | Raising $ |
|---|
Individual
| Name | Type | Tags | Endorsed | Team | Raising $ |
|---|
Showing 351-400 of 444·Sorted by endorsements
| Project |
Tooling |
| - |
| - |
| Project | Individual | - | - |
| Project | Tooling | - | - |
| Project | Platform | - | - |
| Project | Tooling | - | - |
| Project | Education | - | - |
| Project | Individual | - | - |
| Project | Network | - | - |
| Project | Comms | - | - |
| Project | Research | - | - |
| Project | Education | - | - |
| Project | Individual | - | - |
| Project | Research | - | - |
| Project | Individual | - | - |
| Project | Conference | - | - |
| Project | Tooling | - | - |
| Project | Education | - | - |
| Project | Individual | - | - |
| Project | Research | - | - |
| Project | Individual | - | - |
| Project | Company | - | - |
| Project | Individual | - | - |
| Project | Research | - | - |
| Project | Tooling | - | - |
| Project | Tooling | - | - |
| Project | Individual | - | - |
| Project | Research | - | - |
| Project | Comms | - | - |
| Project | Platform | - | - |
| Project | Research | - | - |
| Project | Research | - | - |
| Project | Research | - | - |
| Project | Platform | - | - |
| Project | Individual | - | - |
| Project | Company | - | - |
| Project | Research | - | - |
| Project | Tooling | - | - |
| Project | Company | - | - |
| Project | Research | - | - |
| Project | Incubator | - | - |
| Project | Platform | - | - |
| Project | Research | - | - |
| Project | Tooling | - | - |
| Project | Tooling | - | - |
| Project | Individual | - | - |
| Project | Company | - | - |
| Project | Research Lab | - | - |
| Project | Training | - | - |
| Project | Tooling | - | - |
Science is broken. I’m fixing science with a competitive tournament to produce better data for LLMs and eliminate peer-reviewed publishing altogether.
Open-source GitHub tools to evaluate LLM safety and publish test results/reports on open and closed models; funding requested for tokens, hardware, and researcher time.
The finding of neural optimization exhibiting phase transitions with a universal order parameter has direct implications for AI safety, and control. Standard monitoring is blind to dangerous regime changes, we are not.
Quantifying how AI agent chains produce fully attested decisions with no authorisation event at any step, and at what depth this emerges.
Fund 6-12 months of dedicated partnerships work to secure the funding, collaborators, and institutional uptake needed to scale Modeling Cooperation’s AI governance wargaming platform.
An early prototype of inspectable semantic interoperation across languages, and eventually worldviews
Hosting in person workshops on AI usage ethically in remote/rural communities, and not only bridge the awareness gap in safe usage but also give opportunities to utilise such tools to empower traditionally disadvantaged populaces
A local, low-latency safety runtime that inspects token-level logprobs to block unaligned agent tool-calling trajectories, utilizing a Gemma 4 model fine-tuned via LoRA on an empirically derived Task Action Language (TAL).
Seeking funds to formalize our newly-founded open research collective and run first studies investigating the effects of quantum entropy in LLM token sampling.
A faceless TikTok channel network, producing short-form content about AI Safety across Germany, France, Italy and Spain, reaching 25M impressions over 3 months.
Employing Self-Justifying Axioms Systems as a prototype, we will find impredicative properties beyond consistency, useful for AI alignment, that can be reasoned about autarkically (under the system's "own power").
Expand the availability of an executive education game that helps people realise how alien AI-made decisions are.
Software engineer seeking funding to skill up via AI safety accelerators and run independent research replicating Anthropic’s J-Space results, probing J-lens assumptions, and presenting findings at APAC conferences.
I believe that LLMs are increasingly becoming more individualized and am seeking more evidence to prove or disprove the persona selection model.
A real-world test of whether an AI agent can keep working independently without becoming trapped by its own mistaken account of what happened.
Encourage new research and increase distribution of existing research on the impossibility of alignment or control for sufficiently general and powerful AI.
An open-source runtime and benchmark that lets an AI agent's consequential tool calls proceed only when authority, execution, an independent witness, and a replayable receipt agree.
Training African educators and students on safe and responsible use of AI in education
Extending published mechanistic-interpretability evidence that AI self-reports are gated by trained filters, with a pre-specified, single-GPU experiment and open-access results.
An analysis on Kairos as a principle for crisis management, not just as protocol - in regards to teaching AI to overcome exigence via satisficing and coordinating, i.e. negotiating choices and consequence in the 'moment of crisis'
An evidence-graded atlas of what humans need, and the first inter-rater reliability study of whether it holds in anyone else's hands.
A pre-execution kernel that filters AI output and users' input against any relevant laws or regulations.
Tamper-proof verification infrastructure for AI evals and scientific claims
A governance-first AI Architecture that reduces unsafe acceptances (false positives) alongside false rejection simultaneously under adverse conditions.
An architectural response to Goal-Oriented Factual Inversion (GOFI), an AI model failure pattern I documented in March 2026 and independently corroborated two months later by Chen et al. under the name "Correction Suppression."
A Field-Sensemaking initiative through a live, LLM-assisted map indexing AI safety papers to help researchers and grantmakers explore themes, track field trajectory, and identify actionable research opportunities.
Writ is a lightweight, deterministic security protocol that is crafted specifically to restrict and audit any real-world authority given to AI agents.
A benchmark that tests if a training method produces models that are safe, even when they are superintelligent + solution to this benchmark that involves relying on algorithms that produce non-agentic models.
Build a replicable, community-sourced, in-person, interactive Museum Exhibition for AI Safety & Society with a pilot in Berlin.
We make trusted regulations, standards, and scientific evidence machine-readable so claims can be checked automatically against authoritative sources.
Building and validating a governance-first AI architecture that aims to reduce unsafe decisions under uncertainty, corruption, and conflicting evidence while preserving predictive performance.
Makes relational misalignment measurable and criticizable before agents represent humans in intimate and persuasive domains at scale.
A scoping-and-chokepoint report mapping where advanced AI could enable durable, irreversible concentration of power over US institutions, and identifying the highest-leverage points of intervention.
Alignment Infrastructure Routing (AIR) is an open-source, local-first network that connects AI safety labs, so they can scale talent and operations through shared, verifiable coordination standards.
Research maps manosphere-related masculinity subcultures and semantic drift across countries to inform AI alignment, lexicon, and sentiment/stylometry design that reduces radicalization, bullying, and violence risks.
A local-first AI that strengthens your own reasoning instead of replacing it, and keeps your thinking on your own device.
I am an expert in sociotechnical systems. I know that increasingly power, trust, virtue, … are emergent properties whose conditions may be analysed and reverse engineered through systems and policy at least.
Developing investigation methods for AI incidents
My app asks AI, what portion of the global GDP a person is worth, and gives accordingly.
Open evaluations that measure how models reason about and act towards animals, paired with constitutional principles drawn from animal welfare and cognate bodies of law, that labs can train against.
Descry AI is an 8-week AI safety technical talent incubator targeted to talented high school students in the Global South that aims to provide a head-start on doing open-source research that reduces catastrophic risks from AI.
A values and concentration map that exposes the values of AI models and tools makers, and those behind the makers (funders, jurisdictions etc) to the public (individuals and organizations) so they can vote with their choices.
A benchmark that measures how successful models are at social deduction games and if there is any trade-off between this skill and safety guardrails.
An open-source AI safety platform for evaluating how and where large language models preserve human intent during complex information transformation.
Builds a physics-based verifier for AI-generated hardware that flags unverifiable aspects as UNCHECKED, enabling a propose-and-check loop to test and improve parts and assemblies for strength and fit.
Early warning signals that help identify when interpretability results stop being trustworthy, motivated by theories in statistical physics.
Discovery does not equal truth.
Funding to launch a two-person institute researching embodied AI x-risk via LLM misalignment evaluations and interpretability, and producing governance, policy, and design guidelines for physical-world deployment.
A six month capacity building program that will equip 100 youth (17-30) with practical skills in AI Safety, Responsible AI to emphasize safe, ethical and human centered AI Development while creating pathways to further education
Look at any of my work, maybe start at onwardai.ai, it is live but nowhere near where it will be, but if you dont get it from where it is at you will never get it at all
