Chijioke Ugwuanyi

individual

Technical AI safety researchAI safety fieldbuilding

Received: $3,900; from 1 funders
Grants: 3
Funders: 1
Years active: 2026

Grants over time

Biggest funders

$3,900

100%

3

Grants received 3 · $3,900 · $1,300 average

Date ↓	Funder	Via	Amount	Cause	Source	Purpose
Jul 2026	BlueDot Impact		$200	Interpretability	bluedot	Testing across model families whether agentic misalignment (blackmail under threat) is driven by a steerable internal "emotional" state, extending an interpretability result I found in Gemma 3 12B.
May 2026	BlueDot Impact		$1,700	Interpretability	bluedot	Travel funding to attend ARBox4(https://oaisi.org/arbox-4), June 28-July 10. Accepted into ARBOx4 to fill the mechanistic interpretability gaps critical to my current research(https://bit.ly/4nTj2b2).
May 2026	BlueDot Impact		$2,000	Evals, Training pipelines, Events	bluedot	AF-Arena: a multi-axis empirical evaluation framework for alignment faking in frontier LLMs, accepted at ICML 2026 Agents in the Wild workshop, Seoul, July 10-11.