Ismaël Joffroy Chandoutis

Excited to share Genie 4 today our most realistic and interactive world model: - steer dynamic environments in real time, shaping events, camera angles, and actions - generate native audio matched to the world, from realistic background sounds to characters who can converse in real time! - simulate photorealistic scenes and real-world physics - create more coherent multi-step events through reasoning from Gemini We've started to roll out as a research preview to trusted testers. Coming soon to Google AI Ultra subscribers in Project Genie and early access partners via the Gemini API and AI Studio.

Electroplankton Ableton Live wrapper! Requires the NDS file but runs the ROM unmodified and can control aspects of the Hanenbow stage interface via RAM mod during emulation runtime. Here, fish are triggered via MIDI notes and the audio is processed in Ableton.

Bare Knuckle II (Streets of Rage 2) in the actual streets of Tokyo. I’ve been building an engine to reconstruct games and re-render them in new ways. One of them is spatial rendering. This runs standalone on Meta Quest 3 with a PS5 gamepad.

At just 16, Marcin was already making his guitar sound absolutely mesmerizing. It’s no wonder he’s been called the “Paganini of the guitar”!

Communiqué de l’Académie Goncourt

create your own creative tools

this guy literally explained the truth about the "ADHD superpower"

I rebuilt Nikolayeva's 1992 Variation 25 note by note with AI, then asked another AI to find the human. It found her 26 times out of 51. Chance is 50%.

Introducing FLUX 3 Action. An open weights 7B World Action Model that achieves first place on the RoboLab benchmark. It outperforms the previous best open model by 6.1 percentage points while using 56% fewer parameters and running up to 3.95x faster.⁠⁠ FLUX 3 Action removes the usual trade-off between world action model performance and VLA speed: it still predicts video and actions together, but plans more than twice as far ahead and runs faster per second of robot motion than the strongest open VLA. Teams can fine-tune FLUX 3 Action on their own demonstrations to create policies for a particular robot and task. Together with @nvidia, we also integrated FLUX 3 Action natively into @huggingface's LeRobot, with fine-tuning recipes included and edge deployment on NVIDIA Jetson. Beyond robotics, we’re also seeing promising results training task-specific policies for acting in simulated environments like gaming, controlling a vehicle, computer use, and wherever else a model needs to understand a visual environment and then choose what to do next. FLUX 3 Action builds on the same image, video, and audio pretraining as FLUX 3, but uses a smaller architecture designed for practical deployment. In midtraining, we trained the model to predict actions and future frames together. We’re releasing the weights, code, fine-tuning recipe, benchmarks, and reproducible examples so researchers and developers can build on the model with their own robots, environments, and tasks (see below).

1/ The OpenRouter Batch API is live. For work that doesn't need an answer right now, the Batch API cuts per-token pricing in half on most models and returns everything within 24 hours. Get started: openrouter.ai/blog/announcem…

Introducing Unreal Agent: An open-source harness with state-of-the-art cost efficiency 39% cheaper than Codex+Astra on Terminal-Bench 4.0 while maintaining performance

New essay for @every, by @afterimage We believe we will look back on Astra as a turning point in how creatives use AI in video work. For many months we were experimenting with different AI video approaches: generative workflows in ComfyUI, procedural animation with Python, motion design through the Cavalry and After Effects MCPs, and more. All of these were fundamentally limited by a lack of control. Generative models could sometimes make cool images, but changing one thing without disturbing everything else was difficult. Many of these generative tools weren't (and still aren't) built for true professional workflows. On the other hand, general models starting around Opus 4.5 were decent at writing python code to deterministically edit images and videos, but the models were really bad at “seeing” the images and videos they were supposed to be editing, which made them impractical. The day Astra launched, just from the rumors and marketing, our internal sense was "this might be the one". Then, when we saw the level of 3D detail people were able to achieve with Astra in Blender, we really suspected the model was finally able to "see" and iterate toward things that actually looked good. While everyone raced to build cool (but often useless) demos of 3D worlds, we got interested in something else: compositing 3D assets into live action footage at commercial-grade quality. To this day, we are quite surprised by how few Astra demos focus on this ability. It feels like a breakthrough for us. We tested a range of processes, from traditional VFX skills like masking and tracking to hybrid approaches like compositing Blender renders and generative imagery with real footage. At the highest levels, Astra doesn’t replace someone with true domain expertise in VFX artistry. But, through these tests, it started to feel for the first time that the LLM was actually a viable tool in the kit. It worked well in concert with other tools to make professional results we could actually see ourselves using. The coolest part about all this is that it makes it easy and painless to attempt visual effects on even the smallest projects and most off the cuff videos. We’re excited about the combination of casual footage and visual maximalism. Effects can now be completely over the top without feeling like the whole reason a shot exists. Full "Vibe Check" with video examples & side by side Astra vs Sol comparisons (gift link) ➡️ every.to/vibe-check/vibe-che…