Quentin FEUILLADE--MONTIXI

Karma: 287

I am a former 42.fr student, and SERI Mats 3 scholar. I am currently interested in studying AI with a behavioral approach (Model Ethology). I worked for METR (ARC Eval at the time I worked there) and did independent red teaming for OpenAI and Anthropic. I am a co-founder of PRISM Eval

Thinking Partners: Building AI-Powered Knowledge Management Systems

Quentin FEUILLADE--MONTIXI14 Oct 2025 17:42 UTC

18 points

3 comments10 min readLW link

Investing in Robust Safety Mechanisms is critical for reducing Systemic Risks

Tom DAVID, Pierre Peigné, Quentin FEUILLADE--MONTIXI, Kay Kozaronek and Miailhe Nicolas

11 Dec 2024 13:37 UTC

8 points

3 comments2 min readLW link

Emergence, The Blind Spot of GenAI Interpretability?

Quentin FEUILLADE--MONTIXI10 Aug 2024 10:07 UTC

16 points

7 comments3 min readLW link

Studying The Alien Mind

Quentin FEUILLADE--MONTIXI and NicholasKees

5 Dec 2023 17:27 UTC

80 points

10 comments15 min readLW link

Scalable And Transferable Black-Box Jailbreaks For Language Models Via Persona Modulation

Soroush Pour, rusheb, Quentin FEUILLADE--MONTIXI, Arush and scasper

7 Nov 2023 17:59 UTC

38 points

2 comments2 min readLW link

(arxiv.org)

The Stochastic Parrot Hypothesis is debatable for the last generation of LLMs

Quentin FEUILLADE--MONTIXI and Pierre Peigné

7 Nov 2023 16:12 UTC

52 points

21 comments6 min readLW link

Preface to the Sequence on LLM Psychology

Quentin FEUILLADE--MONTIXI7 Nov 2023 16:12 UTC

33 points

0 comments2 min readLW link

PICT: A Zero-Shot Prompt Template to Automate Evaluation

Quentin FEUILLADE--MONTIXI17 Feb 2023 23:16 UTC

17 points

1 comment11 min readLW link

Using PICT against PastaGPT Jailbreaking

Quentin FEUILLADE--MONTIXI9 Feb 2023 4:30 UTC

26 points

0 comments9 min readLW link