This is powered by Gemini 3. The experiment is called Disco.
The feature is GenTabs. The big shift is this: We move from browsing information
→ to generating interfaces. AI is no longer just answering questions. It is assembling software on demand.
GENERATIVE AI
-
Disco GenTabs: From Information Browsing to AI-Generated Interfaces
By
–
-
Tabs as Intent: Dynamic Interfaces for Your Digital Activities
By
–
The key insight: your tabs are intent. Planning a trip?
→ It becomes a dynamic travel planner. Collecting recipes?
→ A structured meal planning dashboard. Researching space?
→ An interactive solar system explorer. Studying academic papers?
→ A clean, structured learning -
AI Transforms Manual Web Browsing Into Automated Research
By
–
Right now, browsing is manual labor. You: → Open 10 to 20 tabs
→ Compare sources
→ Copy insights into notes
→ Try to connect the dots The cognitive load is on you. This new model flips it. AI reads the context of your open tabs, understands your goal, and builds -
Google’s AI Converting Open Tabs Into Functional Apps Instantly
By
–
What if your 20 open tabs could turn into a working app, instantly?
— Ronald van Loon (@Ronald_vanLoon) 1 avril 2026
That is exactly what @Google is experimenting with right now.
Not a summary.
Not a chatbot.
An actual tool built from your browsing session.
This is the shift most executives are underestimating.
Here’s the… pic.twitter.com/o5Vx7uh367What if your 20 open tabs could turn into a working app, instantly? That is exactly what @Google is experimenting with right now. Not a summary.
Not a chatbot. An actual tool built from your browsing session. This is the shift most executives are underestimating. Here’s the -
SaaS Evolution: Linear Pioneers Agent-Native Software Era
By
–
SaaS isn’t dead, it just needs to become agent-native. Linear (@linear) is a great example of how:
— Dan Shipper 📧 (@danshipper) 1 avril 2026
They pivoted the product to be used by both humans and agents, and that has made them one of the premier software tools in the agent-native era.
I had Linear’s cofounder and CEO… pic.twitter.com/wbgljfcqzXSaaS isn’t dead, it just needs to become agent-native. Linear (
@linear
) is a great example of how: They pivoted the product to be used by both humans and agents, and that has made them one of the premier software tools in the agent-native era. I had Linear’s cofounder and CEO -
Multi-Shot App: Create cinematic scenes from text or images
By
–
The Multi-Shot App makes it easy to go from a simple prompt to a thoughtfully crafted scene. All with dialogue, sound effects and cinematic framing.
— Runway (@runwayml) 1 avril 2026
Start from an image or go purely Text to Video. Available now in the App drawer on the web app. pic.twitter.com/1eRvMCiU6yThe Multi-Shot App makes it easy to go from a simple prompt to a thoughtfully crafted scene. All with dialogue, sound effects and cinematic framing. Start from an image or go purely Text to Video. Available now in the App drawer on the web app. [Translated from EN to English]
-
Large Language Models Need Embodiment: New Neuron Perspective
By
–
The need for embodiment for large language models @NeuroCellPress an open-access perspectiive cell.com/neuron/fulltext/S08…
→ View original post on X — @erictopol, 2026-04-01 14:41 UTC
-
Beginner Analytics Projects with Databricks Free Edition
By
–
Three beginner-friendly analytics projects you can finish in an afternoon with Databricks Free Edition • Analyze a simulated environment using AI/BI Dashboards and AI_Query()
• Explore sample trends and generate predictions with AI_Forecast()
• Load open data with Python and -
Self-Organizing LLM Agents Outperform Predefined Role Hierarchies
By
–
NEW papers on self-organizing LLM Agents. Assign an agent a role, and it'll follow instructions. Let agents figure out roles themselves, and they'll outperform your design. New research tested this across 25,000 tasks with up to 256 agents. The work shows that self-organizing LLM agents spontaneously develop specialized roles without any predefined hierarchy. A sequential coordination protocol outperformed centralized approaches by 14%, agents generated over 5,000 unique roles organically, and open-source models reached 95% of closed-source quality at significantly lower cost. Most multi-agent frameworks today start by defining roles: planner, coder, reviewer, critic. This paper provides large-scale evidence that the opposite approach works better. Give agents a mission, a protocol, and a capable model. The agents will figure out the rest. Paper: arxiv.org/abs/2603.28990 Learn to build effective AI agents in our academy: academy.dair.ai/
-
Achieving 78.9% on OS-world, Outperforming GPT-5.4 at Lower Cost
By
–
Ngl, reaching 78,9% on OS-world and outperforming even GPT-5.4 at 1/10 cost is a big deal