Introducing Parallel Requests for MLX! Multiple requests to the... same model can now be processed simultaneously ✨🚄⚡️ Works both in the API and in Split View chats. See it in action 👇🕺show more

Vibe Design is all about rapid iteration. Now your... tools finally move as fast as your ideas. 🌍✨ Introducing Parallel Editing. ⚡️ Iterate across multiple screens at the same time. You can now fire off edits on multiple screens simultaneously—or spin up 5 different edits of the same screen at once. While "vibe coding" makes you wait line-by-line, Stitch lets you iterate on your entire flow in parallel. Don’t block your creativity.show more

We took a 30B model and split it in... two to write tokens in parallel instead of one at a time. Introducing Nemotron-Labs-TwoTower: a diffusion language model from NVIDIA Research adapted from Nemotron-3-Nano-30B-A3B. Here’s how it works: one half holds the context, the other writes the tokens, with both reusing the pretrained model instead of training a new one from scratch. We found it kept 98.7% of the original model’s quality at 2.42× faster generation.show more

The op kept it for 6 yrs and just... uploaded it this March. There were two kisses: the one in the new video should be the ‘first’ one (you can see the same male staff in both video)show more

Hermes can now search and extract the web on... a fresh install with zero API keys. Behind the scenes, it rotates requests across the public free tiers from Exa, Parallel, Tavily, Firecrawl, and Keenable. If one provider rate limits, Hermes automatically tries the next. Configured backends and API keys still take priority. The keyless ring is a last resort fallback, not guaranteed infrastructure, and it can be disabled entirely.show more

Introducing bunnyOS: the small-model agent and inference platform. Small... language models can now reason, plan, use tools, and take action. We are building the infrastructure to unlock them. Litepaper in bio.show more

Introducing Private Swaps. You can now privately swap supported... tokens on Privacy Cash, powered by the same protocol that has already processed $173M+ in private transfers, and passed 14 audits.show more

OpenAI is working on a new experimental feature for... Codex called Scratchpad. Users will be able to start multiple Codex chats from a TODO list view, which will be executed in parallel. It will become very instrumental in the upcoming Codex Superapp, where you will be able to trigger a broader range of tasks to achieve your goals. * Not available yet 👀show more

Crosschain Swaps are live! Today, we are introducing the... Across Swap API for crosschain swaps in a single call. Bridge and Swap are now one action.show more

Example of how it works in Layout Inspector (now... embedded in Running Devices window). One can view counts and change the recomposition color as well, defaults to Blue.show more

Today I'm launching a very early release of MLX... Model Manager ( A Swift package for quickly and easily adding LLM/VLMs with just a couple of lines of code into your MacOS/iOS applications for local and private inferencing. This is built on the amazing work of the MLX team & what they have done with MLX Model Manager unifies the work they have done with MLXLLM as well as MLXVLM into one package with added abstractions to simplify the usage. I've also added support for Google's new Paligemma2 Vision Model ( You can see a demonstration in the video below! Huge shoutout to Awni Hannun for the creation of MLX, David Koski on leading the charge for MLXVLM and Prince Canuma for the creation of MLX-VLM. Three massive pillars in the MLX community among many others.show more

New free plugin in the works. ⚙️ Create expression... controls for multiple params on multiple layers in one click. Would it be useful in your workflow? Working title Expression Driver. Try it free now on our discord. #aftereffects #aescripts #motiondesignshow more

Introducing MLX-Swift-TS An SDK for running time series foundation... models fully on-device on Apple Silicon. When I joined Datadog, Inc. , I was introduced to Toto, our time series foundation model, and got excited about zero-shot forecasting across different domains. While building a health copilot app, I realized there wasn’t a simple way to run models like these locally on device. So I built one. MLX-Swift-TS exposes a common TimeSeriesForecaster interface for loading and running multiple time series architectures directly in Swift using MLX. No server required. The attached video shows on-device forecasting running inside a native Swift app. Huge thanks to Awni Hannun and the MLX team for building MLX and its Swift API, Prince Canuma for inspiration on MLX SDK patterns, and Ameet Talwalkar and the Datadog team for Toto.show more

Perplexity Computer is massively multi-model. Computer orchestrates models to... run agents in parallel, leveraging Opus to match each task to the model best suited for it. In total, Computer can route work across 19 different models.show more

📢Introducing HertzFlow Alpha Skill: See What Insiders See Drop... any Binance Alpha CA to get full on-chain forensic &insights crystal clear in mins Your AI agent can now see what MMs don't want you to see — powered by @surfdeveloper the only API you need for crypto research 👇show more

The model integrates motifs blending both human and fly... behaviors, making it fit for research work in chimeric cognition and related fields FetterFly is designed to mimic human activity when in view of observers, and to revert to fly behaviors when it believes it is in privateshow more