Coding Tools
Cursor Releases Composer 2.5 Coding Model
Lev Selectorhigh confidence
Why it matters
- →Aims to improve coding efficiency
- →Supports developers in software creation
- →Part of ongoing advancements in coding tools
Cursor has introduced Composer 2.5, a new coding model designed to enhance coding efficiency. This model is part of Cursor's ongoing efforts to streamline coding processes and support developers in creating more robust software solutions.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
How we got here
- 1Cursor Introduces New Frontier Model for Coding
Fireship · April 6, 2026 · Related
- 2Cursor 3.0 Major Update Released
Lev Selector · April 10, 2026 · Background
- 3Composer 2.5 Advances in Coding Model Benchmarks
The AI Daily Brief · May 20, 2026 · Related
What happened next
- 4Cursor launches mobile app for coding agents
TechCrunch AI · June 29, 2026 · Related
- 5Cursor's Origin Launches Amid GitHub Outage
The Rundown AI · August 18, 2026 · Background
- 6Cursor launches Origin to rival GitHub
TechCrunch AI · August 18, 2026 · Related
- 7Cursor Launches GitHub Rival 'Origin'
The AI Daily Brief · August 19, 2026 · Background
- 8Claude Opus 5.5 arrives in GitHub Copilot
GitHub Changelog · September 22, 2026 · Background
Follow this story
Open the full story →Cursor Launches Cheaper Coding Model
2 developments
- May 24 · The AI Daily Brief
Cursor Launches Cheaper Coding Model - May 29 · Lev Selector
Cursor Releases Composer 2.5 Coding Model (This article)↳ Cursor launches Composer 2.5 to improve coding efficiency.
More in Coding Tools
Coding Toolscoding
Claude Code v2.1.323 adds experimental Code Mode and plugin safety
This release quietly introduces Code Mode, an opt-in feature where Claude writes JavaScript to call its own tools, marking a shift toward more autonomous agent-like behavior within the CLI. The update also hardens the plugin ecosystem by enforcing version ranges and adding strict TypeScript type checking for hooks, which should significantly reduce instability from third-party extensions. Beyond these features, the changelog is dominated by critical fixes for authentication drift in background sessions and memory leaks when handling large files, stabilizing the tool for heavy enterprise use.
Claude Code Releases
Coding Toolscoding
llama.cpp b12336 fixes HunyuanVL crash
This release quietly patches a critical memory overflow in the mtmd module that caused crashes when loading HunyuanVL models. The issue stemmed from F64 position embeddings overflowing an F32 buffer, a subtle bug that broke multimodal inference for users relying on this specific architecture. By enforcing strict F32 requirements, llama.cpp stabilizes support for Tencent's vision-language model without adding new features or changing the core API. It’s a necessary maintenance update that keeps local multimodal workflows from breaking unexpectedly.
llama.cpp Releases
Coding Toolscoding
llama.cpp b12343 adds qwen3.5 and ROCm 10
This release quietly extends llama.cpp’s hardware coverage with ROCm 10.0 binaries for both Linux and Windows, finally bringing AMD RDNA/CDNA users into the fold without manual compilation. The standout feature is native support for Qwen3.5 models via tensor merging during conversion, a necessary step as this new architecture gains traction in the open-source community. By shipping pre-built CUDA 13 binaries alongside the older 12.x versions, the project ensures forward compatibility with newer NVIDIA GPUs out of the box. There are no new quantization algorithms or performance breakthroughs here; it is purely an infrastructure update to keep pace with the rapidly shifting landscape of model architectures and GPU drivers.
llama.cpp Releases