Coding Tools
OpenAI expands GPT-6 family with Sol and Luna for Copilot
GitHub Changeloghigh confidence
Why it matters
- →Developers can now optimize costs by routing simple tasks to the cheaper Luna model.
- →Agentic coding workflows gain a dedicated model (Sol) tuned for multistep validation.
- →GitHub Copilot shifts from a single-model experience to a multi-tiered selection strategy.
OpenAI has added two new models, GPT-6 Sol and GPT-6 Luna, to the GitHub Copilot ecosystem. GPT-6 Sol is designed for interactive and agentic coding tasks requiring careful validation, available on Pro+, Max, Business, and Enterprise plans. GPT-6 Luna serves as a lightweight, cost-efficient option for smaller tasks, accessible to all Copilot subscribers including the standard Pro tier. These models join the previously released GPT-6 Astra, allowing users to select the best fit for their needs via the model picker in supported IDEs such as VS Code, Visual Studio, and JetBrains. Administrators can manage access through Copilot settings, with new models enabled by default unless disabled.
Read originalMore from GitHub Changelog
© GitHub ChangelogModels & Labscoding
Claude Opus 5.5 arrives in GitHub Copilot
Anthropic’s latest flagship model is finally inside the IDE, marking a significant shift for enterprise developers who rely on GitHub Copilot. Early benchmarks suggest Opus 5.5 matches its predecessor’s accuracy while consuming fewer tokens and recovering faster from errors in complex agentic workflows. This efficiency gain matters because long-running coding tasks often hit context limits or incur high costs; reducing step count directly lowers friction for multi-file refactoring. The gradual rollout across major IDEs means builders can soon test whether this model handles their most stubborn debugging sessions better than the previous standard.
GitHub Changelog
© GitHub ChangelogMarket & Regulationother
GitHub deprecates SHA-1 SSH keys, adds post-quantum crypto
GitHub is finally killing the legacy ssh-rsa signature type that relies on broken SHA-1 hashes, forcing a shift to stronger rsa-sha2 signatures. Simultaneously, they are introducing mlkem768x25519-sha256, a post-quantum key exchange method, signaling early adoption of quantum-resistant standards in mainstream developer infrastructure. This isn't just a security patch; it's a forced modernization that renders older Git clients and SSH libraries obsolete for GitHub Enterprise users. The move effectively ends the era of weak cryptographic defaults for one of the world's largest code hosting platforms.
GitHub Changelog
© GitHub ChangelogCoding Toolscoding
GitHub Deprecates All-Platform CodeQL Bundle
GitHub is killing the convenience of a single download for CodeQL CLI. Starting with version 2.27.0, the monolithic all-platform bundle is deprecated and will vanish by March 2027. Users must now switch to platform-specific archives, a move that forces CI/CD pipelines to manage separate artifacts for Linux ARM64, x86_64, and macOS. This ends the era of 'one size fits all' distribution for static analysis tooling on GitHub, requiring developers to explicitly target their build environment's architecture.
GitHub Changelog
More in Coding Tools
Coding Toolscoding
Claude Code v2.1.280 adds Opus 5.5 and fixes agent stability
Claude Code just got its first major model upgrade with Opus 5.5 as the new default, bringing a 1M context window and aggressive pricing that reshapes local inference economics. Beyond the headline model swap, this release quietly stabilizes the background subagent system, fixing critical issues where tool lists were rebuilt instead of cached and reports were silently lost during compaction. The UI layer also sees significant polish, with mouse support in fullscreen mode and fixes for Windows terminal rendering that had plagued power users. This is less about new features and more about making the agent runtime reliable enough for heavy, multi-step workflows.
Claude Code Releases
Coding Toolscoding
llama.cpp b11104 adds multi-addr server binding
The llama-server now binds to multiple addresses, a practical upgrade for anyone running local inference behind reverse proxies or complex network setups. This change removes the previous single-address limitation, allowing flexible routing without external workarounds. While the release includes standard binaries for CUDA 13 and ROCm 10.0, the networking feature is the real differentiator here. It makes self-hosted deployments slightly more robust for power users who need granular control over traffic flow.
llama.cpp Releases
Coding Toolscoding
llama.cpp b11105 adds ROCm 10 and Snapdragon support
This release quietly cements llama.cpp as the universal inference runtime by finally bringing full ROCm 10.0 support to both Linux and Windows, closing a long-standing gap for AMD GPU users who previously had to rely on workarounds or older versions. The inclusion of CUDA 13 builds alongside CUDA 12 ensures compatibility with the latest NVIDIA driver stacks without forcing users into beta territory. Perhaps most notably, the addition of native Snapdragon support on Linux marks a significant step toward efficient AI inference on ARM-based mobile and edge devices, expanding the hardware ecosystem beyond traditional x86 and NVIDIA dominance.
llama.cpp Releases