Cosmos Institute granted Nada Amin on August 15, 2025 for Argument Debugger, with funding in the $1K to $10K range plus compute. The award came through the inaugural AI x Truth-Seeking cohort of 27 winners co-funded by Cosmos Institute and FIRE under a $1M program.
Amin is an assistant professor of computer science at Harvard SEAS and leads the metareflection lab, which works on programming-language techniques that combine PL with AI (including LLMs) to produce systems that are correct by construction. She was previously a University Lecturer in Programming Languages at Cambridge, a member of the Scala team at EPFL where she did her PhD, and a software engineer at Google on compiler infrastructure. Her lab's research includes miniKanren-based relational programming, neuro-symbolic AI machines (NSAMs), and "collapsing towers of interpreters" work on staged metaprogramming.
Argument Debugger is positioned as an AI assistant that finds gaps in chains of reasoning and suggests repairs, framed explicitly as a tool for better arguments rather than more persuasive ones. The lab pedigree matters here: Amin's prior work has been about turning informal structures into checkable formal ones, so the project is closer in spirit to a proof assistant or a type-checker for arguments than to a chatbot that critiques rhetoric.
Within the cohort Argument Debugger sits in the evaluation and agents cross-section. Several other AI x Truth-Seeking grants build truth-seeking infrastructure on top of LLMs; Argument Debugger instead operates at the level of an individual argument's structure, which puts it in a thematic cluster with Socratic Mirror and Socratica as the user-side reasoning-improvement tools in the cohort.
Recipient
Nada Amin
Funder
Cosmos Institute · foundation · US
Backs philosopher-builders making prototypes, essays, and projects at the intersection of AI and human flourishing, with emphasis on reason, decentralization, and individual autonomy.
Primary source
https://blog.cosmos-institute.org/p/introducing-the-first-cohort-of-ai
Additional sources
More from Cosmos Institute
- Institute for Decentralized AI launch 2025-09 · 5 fully funded research positions
New institute combining research and infrastructure to support AI that operates without centralized gatekeepers. Initial cohort of five fully funded positions across Oxford and Stanford.
- Metalens 2025-08-15 · $1K-$10K plus compute
Open-source scientific research platform combining AI summarization with structured human checks, intended to help researchers see beyond hype and identify reliable claims in dense literature.
- Perplex 2025-08-15 · $1K-$10K plus compute
Tooling for surfacing hidden goals in closed AI systems by probing them with open-weight reference models. Aims to give independent reviewers a way to audit proprietary deployments.
- Policy Explorer 2025-08-15 · $1K-$10K plus compute
AI tool for analyzing the impacts and assumptions embedded in regulatory and policy proposals, geared toward helping civil-society analysts surface what a rule actually does.
- Remarker 2025-08-15 · $1K-$10K plus compute
Open-source Wikipedia-like reference for exploring truth-seeking behavior in LLMs. Curates examples and methods so other researchers can build on a shared corpus.