[EXTRAIT] Décryptage du fonctionnement d’un LLM en 5min - par Stanislas Polu, CEO de Dust

13 Feb 2024 · 4 min
3:48

Stanislas Polu explains why large language models excel at interpolating from training data but fail at extrapolation, especially in math where problem types shift from algebra to geometry. Self-verification only works in formal mathematics with exhaustive search, and models struggle with truly novel tasks without direction toward the right problem space.

Chapters

More from Stanislas

youtube.com

Dust x Clay - GTM in the Age of AI - full conversation

9mo ago
youtube.com

The Outer-Loop Era - Stanislas Polu - Dust

11mo ago
youtube.com

AI Agents Are Here: What They Can Already Do—and What’s Next

1y ago
youtube.com

AMA with Stanislas Polu, Co-Founder of Dust: Revolutionising Tech with AI Agents

1y ago
youtube.com

Getting the Most From AI With Multiple Custom Agents ft Dust’s Gabriel Hubert and Stanislas Polu

1y ago
youtube.com

Getting the Most From AI With Multiple Custom Agents ft Dust’s Gabriel Hubert and Stanislas Polu

1y ago
youtube.com

Agents @ Work: Dust.tt — with Stanislas Polu

1y ago
youtube.com

dotAI 2024 - Stanislas Polu - LLMs reasoning and agentic capabilities over time

2y ago
youtube.com

No GPU Before PMF // Stanislas Polu // AI in Production Conference Lightning Talk

2y ago
youtube.com

Qdrant x Dust: How Vector Search helps make work work better - Stan Polu | Vector Space Talk #010

2y ago
youtube.com

TCA 2023 Dust / Interview start-up

2y ago
See all content