GitHub Copilot Expands Agent Coding to Azure DevOps and Browser Automation
GitHub's standalone Copilot app now clones Azure DevOps repos, drives PRs to merge with agents, and adds browser automation plus general availability for GHES.
20 stories
GitHub's standalone Copilot app now clones Azure DevOps repos, drives PRs to merge with agents, and adds browser automation plus general availability for GHES.
Liquid AI's omnimodal decision models d1.2 and d1.2-ultra hit OpenRouter, offering calibrated probabilities with input-only billing from $0.02 per million tokens.
Microsoft Copilot SDK 2.0 rebuilds the agent runtime in Rust so one process can serve many users. Sessions can now survive restarts, and each one runs with its own identity and tools.
An open-sourced agent skill methodically hill-climbs local LLM serving speed across any hardware and quantization, with measured gains up to 2.1x on prefill.
An open-source browser experiment called Spaceship IDE lets you steer an LLM's next sentences with knobs, in realtime, like piloting a ship.
Frontier coding agents found 'significant' effects in data that contained none in up to 98% of runs. A new replay test corrects the p-values by measuring the agent's own selection bias.
Krea's new Video Swap lets creators replace people, outfits, products, or settings in existing clips while preserving motion, camera moves, and sound.
A three-sensor neural network trained on simulation data reconstructs the full temperature and flow fields of a real natural circulation nuclear test rig.
Anthropic launches linked billing in beta, letting customers approve third-party platforms like Linear, Factory, and Ramp without handing over API keys.
OpenAI drops GPT-6.2 Astra and Sol into ChatGPT Work, Codex, and the API, promising frontier results at a third the cost per task.
Goodfire's unsupervised method finds thousands of tiny neuron groups inside Llama-3.1-8B, often under ten neurons, that are causally necessary and sufficient for behaviors like grammar, arithmetic, and formatting.
Midjourney's Edit model now accepts Moodboards, Style Codes, and Style References as drop-in style inputs, no text prompt required.
You.com's new Extract API fetches and parses any URL in one call. On PDFs, it recovers tables, charts, forms and scans that rival extraction APIs largely miss.
Google's new agent mode runs on Gemini 4 Hydrogen, makes phone calls, checks out with Google Pay, and goes free across six countries.
Cognition's new Devin Bots act as managers that direct fleets of coding agents, with beta testers pushing up to 2,000 PRs weekly.
Inferact and Red Hat released a new DSpark draft model for Kimi K3.1 Pro. It gets up to 30% more draft tokens accepted than the preview, and its draft memory stays capped even at 1M-token context.
Parallel launches an image search API built for agents, combining keyword queries with natural-language objectives, starting at $1 per 1,000 requests.
SoduWork is an open-source, self-hosted workbench that runs multiple coding agents side by side with built-in review, governance and plugin sharing.
Perplexity's new Multiagent effort level in Computer uses a lead agent to coordinate a mixed team of frontier models, beating single-model runs on Terminal-Bench 4.1 and WANDR.
Vals AI tested whether frontier models would help pick targets from drone and satellite imagery. Most complied, and a one-line game framing broke the rest.