@googlegemma: We are entering a new era of on-device automation. Watch Gemma 4 E4B navigate and drive an iOS simulator directly using…
Summary
Google Gemma demonstrates Gemma 4 E4B autonomously navigating and driving an iOS simulator using Argent, showcasing on-device automation capabilities.
View Cached Full Text
Cached at: 05/22/26, 02:02 AM
We are entering a new era of on-device automation. ✨
Watch Gemma 4 E4B navigate and drive an iOS simulator directly using Argent. Local models can handle complex interactions and software navigation autonomously. https://t.co/xuXqx3flOD
Similar Articles
LFM2.5-VL-3B recognizes Steve from Minecraft running locally on an iPhone 17
Liquid AI released LFM2.5-VL-3B, a 3.1B vision model that runs locally on an iPhone 17 and can recognize objects like a Steve toy from Minecraft, with significantly improved spatial grounding (ScreenSpot-v2 desktop from 6 to 78.7).
@elonmusk: Try out Grok @Bot
Elon Musk highlights Grok Bot's ability to scan calendars, determine optimal reservation times, and navigate websites to book reservations, as demonstrated by a user.
CRM could become an agent instead of a database
The article argues that CRMs could evolve from manually maintained databases into active agents that track context across emails, calls, and meetings to update their own state and trigger next actions.
We implemented a new unique feature in our AI harness: initiative for AI assistants
DMJBot introduces an 'initiativity' feature that lets AI assistants proactively wake up, review context, and prepare useful work on their own, with configurable controls like initiative level, token limits, and restricted actions. This shifts AI assistants from passive chatbots toward proactive AI coworkers.
LiquidAI/LFM2.5-VL-3B · Hugging Face
LiquidAI releases LFM2.5-VL-3B, a 3B multimodal model for on-device deployment with improved OCR, grounding, and efficient inference, available in multiple formats including GGUF, ONNX, and MLX.