Danny Halawi (@dannyhalawi15) 's Twitter Profile
Danny Halawi

@dannyhalawi15

AI Research. Currently @AnthropicAI. Previously @UCBerkeley

ID: 1636564997219430402

calendar_today17-03-2023 03:08:24

50 Tweet

847 Takipçi

1,1K Takip Edilen

Danny Halawi (@dannyhalawi15) 's Twitter Profile Photo
Danny Halawi
@dannyhalawi15

10 days ago

The results in "LLMs Are Superhuman Forecasters" don't hold when given another set of forecasting questions. I used their codebase (models, prompts, retrieval, etc.) to evaluate a new set of 324 questions—all opened after November 2023. Findings: Their Brier score: .195 Crowd