Under the hood, the model does one powerful thing: It splits sound into two parts → → The target sound
→ Everything else That single capability unlocks a lot → → Faster editing for creators
→ Cleaner, more controllable data for AI training
→ Multimodal systems that
GENERATIVE AI
-
AI Model Splits Audio Into Target Sound and Background
By
–
-
AI Audio Tool Adapts to Human Intent Through Multiple Interfaces
By
–
The big unlock is simple but profound: Instead of forcing humans to adapt to audio tools, the model adapts to human intent. You can guide it three ways → → Type what you want, like “keep only the voice”
→ Click where the sound happens in the video
→ Mark a moment in time -
Meta’s AI Audio Editing Tool Simplifies Sound Cleaning
By
–
What if cleaning audio was as easy as clicking on a pixel?
— Ronald van Loon (@Ronald_vanLoon) 20 avril 2026
Not tweaking EQs.
Not guessing with filters.
Just pointing to the sound you want, and telling the AI, keep this.
I’ve been digging into @Meta’s latest work, and it quietly changes how we think about audio editing. pic.twitter.com/xag6nbEavdWhat if cleaning audio was as easy as clicking on a pixel? Not tweaking EQs.
Not guessing with filters. Just pointing to the sound you want, and telling the AI, keep this. I’ve been digging into @Meta
’s latest work, and it quietly changes how we think about audio editing. -
Image Models Generate Surreal Yet Realistic Outputs
By
–
I wish image models could make outputs like this. Absurdity level realism.
-
Grok Expansion: Making AI More Useful Beyond X Platform
By
–
We’re working our ass off to make Grok more usefully intelligent outside of 𝕏
-
Interview with Nous Research CTO on AI Development
By
–
Did you listen to me interview @NousResearch
’s CTO? It went into all of this. -
AI Quality Assurance: Closing Security Gaps in Systems
By
–
Because most aren’t like you. And we are in a dangerous state until the holes get closed. Yeah my AIs can do seemingly anything. You do have to debug. But that step is seemingly easy. “Do a complete quality review.”
-
LLM Reasoning Hidden Internal States Beyond Chain-of-Thought
By
–
LLM Reasoning Is Latent, Not the Chain of Thought? Researcher Wenshuo Wang argues we should study LLM reasoning as the formation of hidden, internal state trajectories, not just the visible "chain-of-thought" text. The paper finds current evidence most strongly supports that
