OpenAI is launching a new user interface for ChatGPT that introduces interactive visuals, enhancing the user experience.
2 editorial reports · 2 verified social mentions. The most authoritative report leads while later evidence completes the story.
What if AI stopped answering with text? 🤔 Andrej Karpathy thinks the future of AI interfaces could look a lot less like ChatGPT and a lot more like a teacher building something specifically for you. For simple questions, AI could explain things using ASD-STE100-style simplified English: short sentences, clear words, and as little ambiguity as possible. But when a topic gets complicated, a wall of text may simply be the wrong interface. Instead, AI could generate a diagram, build a custom interactive webpage, or even create a personal teaching video on the spot, complete with animations inspired by 3Blue1Brown and a synthetic voice. As AI makes coding and content creation dramatically cheaper, generating a temporary interactive lesson for one person and one question starts to make sense. @aipost 🏴
Open mentionTired of taking screenshots, recording screens, and writing paragraph long prompts just to explain simple visual edits. So I built an open-source tool that acts like an agentic canvas letting you point, doodle, and visually direct an agent straight from your workspace. It’s been surprisingly useful across fullstack dev, simulation, and robotics tasks. My main takeaway from building this: visual toolbars and canvas annotations should be standard high level abstraction layers across agentic platforms, customized to specific domains. Curious to hear your thoughts: Does visual direction fit into your current agent workflows? What specific tools/functionality would you want in a visual agent interface? Have Fun! Github Repo: https://github.com/Shahar-Nadiv/colai-clawhub Waitlist For New Feature
Open mention