I'm interested in technical AI safety and alignment, multi-agent systems, and evolutionary computation. I'm currently working on problems in these areas at the Kempner Institute at Harvard.
-
Harvard University
-
17:14
(UTC -12:00) - josephbejjani.com
- in/jbejjani4
- @jbejjani2022
Highlights
- Pro
Pinned Loading
-
ecological-emergent-behavior
ecological-emergent-behavior PublicThe Emergence of Complex Behavior in Large-Scale Ecological Environments
-
deep-leapr
deep-leapr PublicForked from gpoesia/leapr
Programmatic interpretability for reward model debugging
Python
-
perplexing-poem-prompt
perplexing-poem-prompt PublicDo LLMs understand their adversarial prompts?
Python
-
golden-arm
golden-arm PublicWeb application for The Golden Arm, Harvard's student-run movie theater.
Svelte 1
-
works-of-arts
works-of-arts PublicA minimal, responsive artist portfolio, giving control to the artist
TypeScript
-
SlavicGPT
SlavicGPT PublicTraining medium-sized GPTs on scraped Russian text and Slavic literature.
Jupyter Notebook
If the problem persists, check the GitHub status page or contact support.



