Tags: local AI

Perplexity announced Thursday that its Personal Computer AI platform is now open to any Mac user through a new desktop app. The tool, originally limited to Max subscribers and a waitlist, lets autonomous agents access local files, native applications and the web to automate multi‑step workflows. While a Pro or Max subscription is still required to unlock the full feature set, the move signals Perplexity’s push to bring local AI assistants into everyday productivity environments, positioning the service as a safer alternative to competitor OpenClaw. Weiterlesen

Google has introduced Multi-Token Prediction (MTP) drafters for its Gemma 4 open models, promising up to a two‑fold reduction in response time for locally run AI. The experimental feature uses speculative decoding to guess future tokens, allowing a lightweight draft model to fill idle processing cycles. Built on the same architecture as Gemini, Gemma 4 can run on a single high‑power accelerator or, when quantized, on consumer‑grade GPUs. A shift to an Apache 2.0 license also makes the models more permissive, encouraging broader adoption of edge AI. Weiterlesen

Microsoft is testing a new AI agent that mimics the open‑source OpenClaw tool but runs within its Microsoft 365 Copilot suite. The company says the feature, aimed at enterprise customers, will offer tighter security controls and operate continuously to handle multistep tasks. While the agent could run on local hardware, Microsoft has not confirmed its deployment model. The firm plans to showcase the technology at its Build conference in June, following a series of recent Copilot‑related launches. Weiterlesen

Ollama, a runtime for running large language models locally, announced preview support for Apple’s open‑source MLX framework and added Nvidia’s NVFP4 compression format. The update targets Apple Silicon Macs, requiring at least 32 GB of RAM, and currently supports Alibaba’s 35‑billion‑parameter Qwen 3.5 model. These changes aim to improve caching, memory efficiency, and overall speed, aligning with growing interest in running AI models on personal machines amid frustrations with cloud‑based rate limits and subscription costs. Weiterlesen

Anthropic has introduced Claude Cowork, a new feature that gives its Claude AI direct access to local folders on macOS. Available as a research preview for Claude Max users, the tool lets the AI read, edit, and create files, handling tasks such as sorting documents, summarizing notes, drafting reports, and preparing presentations. The system places the user in a supervisory role, offering approval prompts before major changes. By moving AI assistance from the cloud to the local file system, Claude Cowork aims to reshape how people interact with their computers while acknowledging risks like unintended file edits. Weiterlesen

Open Notebook is an open‑source project that mirrors many of the capabilities of Google’s NotebookLM while emphasizing privacy and flexibility. Users can feed documents, web links, or plain text into the system, then generate summaries, flash cards, audio overviews, and more. Unlike NotebookLM, which runs in the cloud, Open Notebook can be run locally using Docker and a choice of language models, keeping data on the user’s device. The setup is more technical, requiring familiarity with containers and Linux, but the community offers guides and support. The tool expands knowledge‑base search, multi‑notebook sourcing, and customizable podcast creation, positioning it as a compelling option for users who prioritize control over their AI interactions. Weiterlesen

Microsoft announced that Notepad’s AI writing tools will soon run locally on Copilot+ PCs, eliminating the need for a subscription for those features. The change lets users choose between on‑device and cloud generation. At the same time, Paint receives project‑saving capabilities and an opacity slider, while Snipping Tool adds a quick markup option. All updates are rolling out to Windows Insider Canary and Dev channels, giving early testers access to the new functionality. Weiterlesen