Josef Chen PRO

josefchen

·

https://josef.cn

josefchen

AI & ML interests

Food

Recent Activity

updated a dataset about 4 hours ago

josefchen/co-failure-67-models

updated a Space about 4 hours ago

josefchen/orchestration-is-allocation

updated a Space about 1 month ago

josefchen/flavourbench

View all activity

Organizations

josefchen 's Spaces 4

Combining LLMs Rarely Beats the Single Best Model

beta=P(all wrong): the co-failure ceiling on LLM ensembles

FlavourBench

Explore and compare LLM performance on the FlavourBench leaderboard

Ready Cohorts Explorer

Explore GPU-ready cohorts for deterministic agent control.

The Physical AI Inference Gap in Batch-1 LLM Decode

Interactive companion to the batch-1 LLM decode paper