---
title: About | Joey David
description: About Joey David: experience, education, recommendations and links.
canonical: https://joeydavid.fyi/about/
markdown: https://joeydavid.fyi/about/index.md
---

# About | Joey David

> Experience, education, technical stack, reading/music recommendations and contact links.

Researcher at [MILeS](https://miles.lamsade.fr/) (CNRS, Dauphine-PSL), continuing the work on LLM reasoning from my internship there.
I'm also wrapped up in recursive self-improvement, emergence and AI safety.

## Experience

### MILES, LAMSADE (Paris)

- **Researcher**, Late 2026 – present: Continuing my internship work on LLM reasoning.
- **Research Intern**, Apr–Oct 2026: Behavioral rate of fine-tuning via LoRA compression ([arXiv](https://arxiv.org/abs/2611.06598)).

### INSA Lyon, DISP (Lyon)

- **Student Researcher**, 2025–2026: Semi-supervised uveitis localization in fundus scans.

### Sopra Steria (Lyon)

- **SWE Intern**, 2024: NLP CV analysis and full-stack features for Storengy.

## Education

### ENS-PSL / Mines / Dauphine (Paris)

- **M.Sc. AI & Data Systems**, 2025–2026

### UCBL (Lyon)

- **M.Sc. CS (M1)**, 2024–2025

### Oregon State University (Corvallis)

- **Exchange**, 2023–2024

### UCBL (Lyon)

- **B.Sc. Computer Science**, 2020–2023

## Stack

- **Interests**: Reasoning, Interpretability, RL, Information Theory, AI Safety
- **Languages**: Python, C++, CUDA, TypeScript
- **Tools**: PyTorch, JAX, Hugging Face, vLLM, Docker, Linux

## Recommendations

### Articles

#### Reasoning

- [Less is More: Recursive Reasoning with Tiny Networks](https://arxiv.org/abs/2510.04871) (Jolicoeur-Martineau et al. · 2025)
- [LLM Reasoning as Trajectories: Step-Specific Representation Geometry and Correctness Signals](http://arxiv.org/abs/2604.05655) (Sun et al. · 2026)
- [Equilibrium Reasoners: Learning Attractors Enables Scalable Reasoning](http://arxiv.org/abs/2605.21488) (Huang et al. · 2026)
- [How to think step-by-step: A mechanistic understanding of chain-of-thought reasoning](http://arxiv.org/abs/2402.18312) (Dutta et al. · 2024)

#### Interpretability

- [Emotion Concepts and their Function in a Large Language Model](https://www.anthropic.com/research/emotion-concepts-function) (Sofroniew et al. · 2026)
- [Explainable Chain-of-Thought Reasoning: An Empirical Analysis on State-Aware Reasoning Dynamics](http://arxiv.org/abs/2509.00190) (Yu et al. · 2026)
- [Emergent Symbolic Mechanisms Support Abstract Reasoning in Large Language Models](https://arxiv.org/abs/2502.20332) (Yang et al. · 2025)

#### Neuroscience

- [The Abstraction Fallacy: Why AI Can Simulate But Not Instantiate Consciousness](https://deepmind.google/research/publications/231971/) (Lerchner · 2026)
- [Large and fast human pyramidal neurons associate with intelligence](https://elifesciences.org/articles/41714) (Goriounova et al. · 2018)
- [Predictive processing and relevance realization: exploring convergent solutions to the frame problem](https://www.semanticscholar.org/paper/Predictive-processing-and-relevance-realization%3A-to-Andersen-Miller/c441ffdb7343b61e66b074c0ad6e947cdb919bb0) (Andersen et al. · 2022)
- [A critique of pure learning and what artificial neural networks can learn from animal brains](https://www.nature.com/articles/s41467-019-11786-6) (Zador · 2019)

### Books

- *A Brief History of Intelligence* by Max Bennett
- *Antifragile* by Nassim Nicholas Taleb
- *The Mind Is Flat* by Nick Chater
- *Godel, Escher, Bach* by Douglas Hofstadter
- *Dune* by Frank Herbert
- *Oyasumi Punpun* by Inio Asano

### Music

- *Le voyage de Penelope* by Air
- *Echoes* by Pink Floyd
- *Tears of the Star* by CASIOPEA
- *I'm Not Human At All* by Sleep Party People
- *Touch (Drumless)* by Daft Punk
- *Supplique pour être enterré à la plage de Sète* by Georges Brassens
- *Rockets Fall on Rocket Falls* by Godspeed You! Black Emperor

## Contact and elsewhere

- [Resume (PDF)](https://joeydavid.fyi/media/joey_david_resume_2026.pdf)
- [Email](mailto:joeydhp@protonmail.com)
- [Scholar](https://scholar.google.com/citations?hl=en&user=J3oOQioAAAAJ)
- [GitHub](https://github.com/joey-david)
- [Twitter/X](https://x.com/t0rt0ised)
- [Admonymous](https://www.admonymous.co/joey-david)
- [LessWrong](https://www.lesswrong.com/users/jdavid)
- [Beat me at chess](https://www.chess.com/member/1d42c43nc3)

## Site map

- [Home](https://joeydavid.fyi/index.md): Overview: current position, recent research and selected projects.
- [Research](https://joeydavid.fyi/research/index.md): Papers, master's thesis and ongoing research, with arXiv, PDF and code links.
- [Projects](https://joeydavid.fyi/projects/index.md): Main ML/agent projects, side projects and Android apps, with repos and demos.
- [About](https://joeydavid.fyi/about/index.md) (this page): Experience, education, technical stack, reading/music recommendations and contact links.
- [llms.txt](https://joeydavid.fyi/llms.txt): site index for language models; [llms-full.txt](https://joeydavid.fyi/llms-full.txt) has every page in one file.