@ms_aifrontiers: What it is: a family of agents that do real browser work like filling out forms and making reservations. Pixel-to-actio…
Summary
Microsoft AI Frontiers releases a family of browser agents that can fill forms and make reservations using pixel-to-action with observe-think-act loops. Available in 4B, 9B, and 27B parameter sizes for deployment on modest hardware.
Similar Articles
@ms_aifrontiers: Along with MagenticLite, we're introducing Fara1.5: a family of small browser agents at 4B, 9B, and 27B. It scores 63% …
Microsoft introduces the Fara1.5 family of small browser agents (4B, 9B, 27B) that achieve state-of-the-art performance on computer use benchmarks, scoring 63% on Online-Mind2Web and beating larger models like Operator and Gemini.
AI agents are one prompt injection away from doing something you'd never ask them to do. We built a fix.
PixieBrix launches Agent Browser Shield, a free source-available browser extension that protects AI agents from prompt injection, dark patterns, and context pollution during web browsing.
@_vmlops: MICROSOFT'S FARA-7B CAN USE YOUR COMPUTER FOR YOU 7b params...clicks, scrolls, fills forms, books tickets all on its ow…
Microsoft released Fara-7B, a 7-billion parameter small language model that can autonomously control a computer to perform tasks like clicking, scrolling, and filling forms, running on-device and beating larger models like OpenAI's computer-use agent on benchmarks.
@shawn_pana: Proactive agents are the future We're building Agency in Browser Use Box > Agents propose goals and tasks to complete >…
A new tool called Agency in Browser Use Box enables AI agents to propose goals and tasks, with humans accepting or rejecting them and agents notifying progress.
@ms_aifrontiers: Fara1.5 is here! The tech report just landed on arXiv. New SOTA for computer use agents of its size, and it competes wi…
Fara1.5 is a family of native computer use agents trained using the FaraGen1.5 scalable data pipeline. The models achieve new state-of-the-art results on browser-use benchmarks, competing with much larger frontier models.