A focused feed of models, agents, research and open-source releases for people building with AI.
Cognition is acquiring Corridor , folding its team into Devin Security . Corridor co-founders Jack Cable and Ashwin Ramaswami, both ex-CISA, are joining Cognition. Deal reunites them with Alex Stamos, now Cognition's CSO after a stint leading Corridor security.
Multi-account switching lands on Claude iOS and Android , no more sign-out dance between work and personal. Voice mode now works with Apple CarPlay on iPhone for hands-free driving conversations.
Jev and winnow:e4b matched the reference on all 12 Claude Code fixes, Claude in a plain message matched 9, and a filename rule matched 3. Only one of the 12 fixes left a bug behind, and all four pickers caught it, so the test measures fit and says nothing yet about catching more bugs.
Gemini now lets you generate, preview, and edit files like PDFs, docs, slides and spreadsheets inside the chat . Highlight any passage and ask Gemini to rewrite text or revise visuals without leaving the preview.
Zed announced DeltaDB , a Git-compatible version control system for agent context and conversations. Every human or agent edit becomes a delta in a causal DAG, linking code to the conversation that produced it.
Mistral released the open weights for its 1-trillion parameter Mistral Large 4 model, now leading open-weight coding benchmarks with multimodal input and cyberdefense tuning.
Runway launched Character Swap inside App Studio for recasting video characters or locations Preserves original motion using depth-map guided keyframes plus Seedance 2.5 Supports audio transfer or full audio swap to match the new scene Replace people or settings from a reference image or text
Poolside's 225B Mixture-of-Experts coding model lands with open weights, 262K context, and benchmark scores rivaling frontier closed systems.
An independent 4B fine-tune of Qwen3.5 turns plain text prompts into self-contained Three.js scenes, with weights, dataset, and GGUFs public.
Microsoft Research and UC Berkeley released TokenEconomizer , a plugin cutting coding agent costs 18-30% on SWE-Bench. Works with Claude Code, Codex, GitHub Copilot CLI, and Pi without modifying the agent itself.
OpenAI is now bundling monthly API credits into ChatGPT Pro and Business subscriptions, turning consumer plans into a launchpad for building apps and agents.
Google open-sourced EGM, a plugin that uses deep-context agents to draft software specs and zero-context subagents to tear them apart before any code is written.
Microsoft's new managed agent harness in Foundry handles orchestration, tools, context, and sandboxing so developers can skip rebuilding the execution layer.
GitHub's new runtime orchestration layer routes between Claude and GPT models, scoring near Opus 5.5 at half the cost per task.
Zed 1.26 ships expandable variable inspection in debugger hovers, built-in Pyrefly for Python, and DWARF debugging for WebAssembly sources in the JS debugger.
Claude for Legal rolls out a gallery of prebuilt artifacts for contract review, cite checking, and regulatory scans, plus 60+ connectors.
SemLoc turns LLM program reasoning into runtime-checkable constraints, boosting Python fault localization Top-1 accuracy from 6.4% to 42.8% over spectrum baselines.
Cursor's new Annotate feature lets you point, draw, and type on your running app so the agent can edit the right code.
Arena's Agent Mode now plugs directly into Gmail, GitHub, Linear, Notion, Vercel, Supabase and more, replacing the copy-paste shuffle between tabs.
Zed's Delta team ships a share command that turns Claude Code sessions into live, multi-developer threads with synced worktrees and uncommitted edits.
Cognition's new coding benchmark tests whether agents respect unstated constraints, with top model Opus 5.5 scoring just 45% on tasks maintainers built over 40+ hours each.
Replit Cloud Agents let non-engineers submit tested pull requests to production codebases, with video evidence and engineer approval before merge.
Dossier is an open-source, self-hosted job hunting app that pairs your profile with a local or hosted LLM to draft tailored resumes, cover letters, and track every application.
A six-page follow-up uses Hypothesis to stress-test the recent DeepMind softmax fix, finds a new edge case, and ships a tougher implementation.
No stories match these filters.
