Nazanin Jafari
@nazaninjafari.bsky.social
Cs @UMass
NLP researcher
Currently working on LLM safety and factuality and hate speech moderation
NLP researcher
Currently working on LLM safety and factuality and hate speech moderation
Reposted by Nazanin Jafari
Introducing 🐻 BEARCUBS 🐻, a “small but mighty” dataset of 111 QA pairs designed to assess computer-using web agents in multimodal interactions on the live web!
✅ Humans achieve 85% accuracy
❌ OpenAI Operator: 24%
❌ Anthropic Computer Use: 14%
❌ Convergence AI Proxy: 13%
✅ Humans achieve 85% accuracy
❌ OpenAI Operator: 24%
❌ Anthropic Computer Use: 14%
❌ Convergence AI Proxy: 13%
March 12, 2025 at 2:00 PM
Introducing 🐻 BEARCUBS 🐻, a “small but mighty” dataset of 111 QA pairs designed to assess computer-using web agents in multimodal interactions on the live web!
✅ Humans achieve 85% accuracy
❌ OpenAI Operator: 24%
❌ Anthropic Computer Use: 14%
❌ Convergence AI Proxy: 13%
✅ Humans achieve 85% accuracy
❌ OpenAI Operator: 24%
❌ Anthropic Computer Use: 14%
❌ Convergence AI Proxy: 13%
چقدر توییتر حال به هم زنه اصلا دو دقیقه نمیشه تحملش کرد یکم رفتم ببینم چه خبره چی میشه که دیدم همش پروپاگاندای ماسک 🤢
March 1, 2025 at 5:19 PM
چقدر توییتر حال به هم زنه اصلا دو دقیقه نمیشه تحملش کرد یکم رفتم ببینم چه خبره چی میشه که دیدم همش پروپاگاندای ماسک 🤢
Reposted by Nazanin Jafari
Looking for an emergency reviewer for a CHI Late Breaking Work submission (8 pages) on Black people's experience with LLMs. Please DM if you have capacity to review! Deadline is on the 14th.
February 12, 2025 at 6:01 PM
Looking for an emergency reviewer for a CHI Late Breaking Work submission (8 pages) on Black people's experience with LLMs. Please DM if you have capacity to review! Deadline is on the 14th.