Coding Tools
GitHub Copilot Introduces Auto Model Selection Tiers
GitHub Changeloghigh confidence
Why it matters
- →Offers users more control over AI model selection based on task requirements.
- →Enhances cost management by allowing users to prioritize efficiency or quality.
- →Improves usability by tailoring AI performance to specific needs.
GitHub has introduced a new feature for Copilot that allows users to select from three tiers of auto model selection: efficiency, balance, and intelligence. Each tier optimizes for different aspects such as cost, quality, and response time, enabling users to tailor the AI's performance to their specific needs. This feature is being rolled out in Visual Studio Code, Copilot CLI, and the GitHub Copilot app. The move aims to provide users with more control over how Copilot selects models, enhancing both flexibility and cost management.
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
- 1GitHub Copilot Enhances Model Selection in VS Code
GitHub Changelog · May 20, 2026 · Same story
- 2GitHub Copilot App Now Supports Any Model Provider
Matt Wolfe · June 10, 2026 · Same story
- 3GitHub Copilot Enables Auto Model Selection for Enterprises
GitHub Changelog · July 1, 2026 · Same story
More in Coding Tools
Coding Toolscoding
Claude Code v2.1.316: Subagents and Gateway Budgets
Anthropic is tightening control over Claude Code's autonomous behavior with new environment variables that let you disable 'ultrathink' or cap subagent effort levels. For teams, the introduction of pooled group budgets on the gateway allows shared monthly spending limits across members, a practical fix for enterprise cost management. The release also patches critical bugs where shell commands would hang or crash on exit, stabilizing the developer experience significantly.
Claude Code Releases
Coding Toolscoding
llama.cpp b12022 adds ROCm 10 and Snapdragon support
This release quietly cements llama.cpp as the universal inference runtime by finally bringing ROCm 10.0 to Linux and Windows alongside CUDA 13.4, effectively closing the hardware gap for AMD users who were previously left behind. The inclusion of native Snapdragon support on Linux marks a significant step toward running local LLMs on ARM-based mobile chips without emulation overhead. While KleidiAI on Apple Silicon is disabled in this build, the broader expansion to diverse accelerators ensures that developers aren't locked into NVIDIA ecosystems anymore.
llama.cpp Releases
Coding Toolscoding
llama.cpp b12023 fixes shared prefix bug
This release addresses a specific inference artifact where decision prefixes were incorrectly bleeding into output embeddings. By capping shared prefixes at the first output position, llama.cpp ensures that option tokens remain distinct for parent and child tasks. This is a targeted fix for multi-step reasoning or voting workflows rather than a performance boost. It stabilizes complex generation patterns without changing the underlying model architecture.
llama.cpp Releases