Cover Image for Constructability: Designing plain-coded AI systems – Charbel-Raphaël Ségerie & Épiphanie Gédéon
Cover Image for Constructability: Designing plain-coded AI systems – Charbel-Raphaël Ségerie & Épiphanie Gédéon
Avatar for Guaranteed Safe AI Seminars
Monthly seminars on topics related to Guaranteed Safe AI. https://www.horizonevents.info/guaranteedsafeaisem…
71 Going

Constructability: Designing plain-coded AI systems – Charbel-Raphaël Ségerie & Épiphanie Gédéon

Zoom
Registration
Past Event
Welcome! To join the event, please register below.
About Event

Constructability: Designing plain-coded AI systems

Charbel-Raphaël Ségerie & Épiphanie Gédéon – Executive director at CeSIA & Independent Researcher

Current AI paradigms lead to inscrutable black-box systems that make it particularly hard to examine how they work or what they actually do. In this talk, we present constructability, a different approach to AI systems leveraging automatic LLM (or other kind thereof) usage in order to train and design systems that are interpretable and reviewable by-design. This talk will present both the broader idea and how actually feasible it could be right now, along with prototypes for this idea and research directions.

GS AI seminars

​​​The monthly seminar series on Guaranteed Safe AI brings together researchers to advance the field of building AI with high-assurance quantitative safety guarantees.

Avatar for Guaranteed Safe AI Seminars
Monthly seminars on topics related to Guaranteed Safe AI. https://www.horizonevents.info/guaranteedsafeaisem…
71 Going