6-Months Full-Time Mech Interp Research:Inference-Time Safety Without Retraining

Fund for living expenses to build a two-layer inference-time safety architecture on Llama-3 8B - geometric trajectory bounding paired with activation steering.

ConsciousAI: Architectural Deliberation Layer for LLM Safety

Model-agnostic R-Cycle / 4-voice / Oath-Lock protocol that reduces LLM reactivity at the orchestration layer. DOI-published. Working code. Solo founder.

Independent Interpretability Research on Detecting Deceptive Behaviors in LLMs

African Livestock AI Evals: Benchmarking LLMs on Nigerian Agricultural Knowledge

The first AI safety evaluation benchmark for Nigerian indigenous livestock systems testing whether frontier models are safe to deploy in African food systems.

Funding for ICML attendance 2026

Requesting funding for ICML 2026 spotlight position paper on ML safety for combating intimate partner violence

Behavioral Audits for Epistemic Reliability

Detecting the EC–EpC gap in deployed LLMs: when AI systems sound credible but misrepresent their own knowledge boundaries.

Falcon Fund

A new fund for animal welfare, AI-pilled

Retroactive: Travel for two ICLR 2026 workshop papers (Rio)

Two co-authored workshop papers (LLM reasoning, agentic-AI accountability), presented April 2026 in Rio. Asking partial trip reimbursement.

CHINI-bench + CHINI-train: a deterministic simulator for AI evaluation and RL

If your reward model is an LLM, you cannot tell whether the policy is gaming the reward or actually getting better. We built a simulator instead.

Golem Physics + Constraint Native: Verification Before Voice & Action

Funding the open-source launch of a working claim-state system and the local firewall bridge that carries verification before voice into governed agent action.

Videos covering AI news and politics with a focus on the extinction threat

Social media content across YouTube, Instagram, and TikTok to grow AI x-risk awareness and build political momentum for a global pause.

Decoding Logic: Mechanistic Interpretability in LLMs in a research program

Identifying and auditing reasoning circuits in LLMs within Algoverse 2026 using Sparse Autoencoders (SAEs).

University of Chicago Harris MA for AI Governance and Catastrophic AI Risk

Urgent funding needed by May 8 for graduate policy training focused on AI governance

Modeling AI competition dynamics for better governance

Software tools and research to quantify coordination failures and inform policy decisions.

Whitebox — AI consciousness and agency risk measurement and certification

Developing enforceable architectural constraints, safety mechanisms, and certification criteria to keep advanced AI systems aligned and non-conscious

Lyptus Research: Bridge Funding

An early-stage AI safety research group based in Sydney, Australia

TELL: The AI Detector You *Don't* Have To Trust

Putting explainability at the forefront of AI text detection

AI Understanding: Scaling Safety via Interactive Simulations

Building the first browser-based digital laboratory for interactive AI Safety education and failure-mode discovery.

Epistemic Curie Benchmark: measuring phase transitions in LLM epistemic autonomy

First quantitative framework for measuring when LLMs surrender independent reasoning under authority pressure

Precautionary AGI Governance

Limited Legal Personhood as a Reversible Safety Instrument