ai Sep 24 The Qodo Agentic Toolbox: A CLI-powered Quality counterpart for coding agents The gap between what an AI coding agent can reason about and what it can actually do on a developer's machine is narrowing fast, but it is still a gap. An agent can draft a function, but can it run the tests, update the changelog,... ai Sep 24 Show HN: Whiteboard (YC W26) – An open-source IDE for thoughtful software design The idea that an AI agent can write code is well established. The harder problem is getting the agent to explain what it wrote, why it chose that approach, and how its decisions map to the original requirements. Whiteboard, an ope... ai Sep 24 LLMs can write tool workflows. Will they choose to? When an AI agent can either call tools directly or write a Python program to call those same tools inside a sandbox, the assumption is that it will pick whichever route is more efficient. A new technical benchmark from researcher... ai Sep 24 The Gnome LLM Policy That I Want The debate over whether AI-generated code belongs in open-source projects has moved from discussion forums to formal policy proposals. KDE recently made headlines with a controversial plan to define an official stance on large lan... ai Sep 24 Gemini 3.8 with Live Avatar Google has moved its multimodal voice AI agent platform from preview into general availability, adding a visual avatar layer that allows conversational agents to display a face that moves in sync with speech. The feature, called G... ai Sep 24 Cheaper LLM Labelling When Simon Willison needed to classify roughly 21,000 Git commits as either maintenance or new development, the obvious approach was to call an LLM for each one. The catch was that at roughly 1.5 seconds per call, the process woul... ai Sep 24 UkisAI Swift Series / 27B, Flash Next and Bonsai 2 /-63.4% thinking, x1.95 speed UkisAI has released the Swift family of efficient reasoning models, a set of Qwen-based LLMs designed to solve one specific problem that has plagued large reasoning models: they think too much. The company's previous model, Swift... ai Sep 24 Muse sure looks a lot like OpenClaw The consumer AI agent landscape shifted dramatically over the past year, and the timeline reads like a case study in how an open-source project can redirect the strategy of the largest technology companies in the world. At the cen... programming languages Sep 24 Muse will apparently let you download its entire filesystem Two weeks after a researcher discovered a vulnerability that let attackers hijack the Muse AI agent, a pair of independent developers have found a second way to extract Meta's internal platform data: by simply asking the AI to sha... ai Sep 24 Meta made a Tamagotchi-like wearable for its Muse AI agent Meta has unveiled a palm-sized AI wearable called Muse Charm, a keychain-sized device that gives consumers a physical way to interact with its Muse AI agent. CEO Mark Zuckerberg introduced the gadget during a "one more thing" mome...