Sebastien Bubeck
VERIFIED TECHNICAL DOSSIERSources checked

Sebastien Bubeck

VP of GenAI Research, Microsoft | Author of Sparks of AGI & Phi Model Architect

2 Verified ArtifactsSource Checked & Attributed

Verified Proof of Work Artifacts

2 items cataloged

Each artifact below represents an authenticated research publication, production code repository, or technical architectural framework directly authored or co-created by Sebastien Bubeck. Every entry undergoes editorial source verification.

#1
RESEARCH Checked Sep 23, 2026

Textbooks Are All You Need (The Phi Model Series)

Demonstrated that a 1.3-billion parameter transformer trained on 6 billion tokens of curated synthetic 'textbook quality' data achieved 50.6% on HumanEval, dramatically outperforming models 10x its size trained on hundreds of billions of uncurated web tokens.

Model & Execution Context:Phi-1 and Phi-2 autoregressive models trained on synthetic Python exercises and educational textbooks curated by GPT-3.5.
Scope & Limitations

Synthetic data diversity must be aggressively managed to prevent model collapse and repetition loops on out-of-distribution prompts.

#2
RESEARCH Checked Sep 23, 2026

Sparks of Artificial General Intelligence: Early experiments with GPT-4

Authored the 154-page seminal investigation demonstrating that early non-multimodal GPT-4 exhibited emergent general intelligence across mathematics, coding, law, vision-via-code, psychology, and medicine without domain-specific fine-tuning.

Model & Execution Context:Unconstrained early GPT-4 base model checkpoint evaluated across novel out-of-distribution reasoning probes.
Scope & Limitations

Highlighted critical remaining flaws including lack of long-term planning, working memory degradation, and blind confidence in false premises.