
Anthropic has rolled out Claude Sonnet 5.5, an update to its mid-tier model offering improved performance across various tasks. In a move to expand developer utility, Anthropic also announced 'Claude Code Mods,' a feature allowing the community to create and share modifications for the Claude Code CLI tool. This ecosystem expansion aims to make coding assistance more customizable and powerful.
Read originalEarlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
TechCrunch AI · June 30, 2026 · Same story
AI News · July 1, 2026 · Same story
The Rundown AI · July 1, 2026 · Same story
AI Explained · July 2, 2026 · Same story
Lev Selector · July 3, 2026 · Same story
Duncan Rogoff · September 23, 2026 · Same story
GitHub Changelog · September 28, 2026 · Same story
Claude Code Releases · September 30, 2026 · Same story
© Matt WolfeAI agent platform Strands introduced Decider 2B, a specialized small language model designed for autonomous decision-making tasks.
© Matt WolfeElevenLabs launched its v4 voice model for higher fidelity audio, while Microsoft introduced MAI-Voice-2.1 and a new streaming transcription model.
© Matt WolfePresident Trump signed an executive order establishing a framework for the development and regulation of AI superintelligence.
This release stabilizes the core session management of Claude Code, specifically targeting the fragile state of resumed conversations where context or thinking traces were previously lost. It also patches critical reliability issues in the Model Context Protocol (MCP) integration, ensuring tool calls don't duplicate or hang indefinitely when remote servers misbehave. The addition of $.ui.selection() for mods and better GitHub CLI handling in cloud sessions shows a focus on developer workflow friction rather than new capabilities. These are necessary maintenance updates that make the tool more robust for heavy daily use.
This release is a classic maintenance patch for Claude Code, focusing on stabilizing the terminal interface and tightening security rules. It fixes critical bugs where deny/ask rules were bypassed in nested shell commands or via symlinks, ensuring sandbox policies actually hold. The update also resolves numerous UI freezes caused by malformed HTML tags and plugin rendering errors, making the agent feel less brittle during complex coding sessions.
This release tackles the notorious memory hunger of long-context inference for Qwen4-exp models by halving indexer score memory. The optimization works by computing head scores in place rather than materializing separate tensors, a change that significantly reduces VRAM pressure during heavy workloads. Beyond memory efficiency, b11372 expands hardware coverage with CUDA 13 support and Vulkan tiling for the lightning indexer. It also adds ROCm 10.0 binaries, keeping AMD users in step with NVIDIA's latest driver ecosystem. The result is a leaner runtime that handles extended contexts without hitting out-of-memory errors as quickly.