Coding Tools
GitHub adds AI Scan security metrics
GitHub Changeloghigh confidence
Why it matters
- →Security teams can now measure autofix adoption rates to evaluate AI tool effectiveness.
- →Metrics help justify investment in AI security by tracking remediation trends over time.
- →Separation of CodeQL and AI Scan data allows for clearer performance analysis.
GitHub has released new metrics in its Security Overview for organizations and enterprise administrators using AI Scan for pull requests. The update tracks the number of findings generated, resolved issues, remediation rates, and how often developers apply autofix suggestions. The interface now separates CodeQL and AI Scan data under distinct tabs on the 'Code scanning on pull requests' page. This public preview is available on GitHub.com and GitHub Enterprise Cloud for customers with Code Security or Advanced Security licenses.
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
- 1OpenAI, Hugging Face address security incident
OpenAI · July 21, 2026 · Background
- 2AI Enhances Vulnerability Response in Cybersecurity
AI News · August 11, 2026 · Background
- 3GitHub Launches AI Scan API for Pull Requests
GitHub Changelog · September 10, 2026 · Same story
- 4GitHub adds AI Scan enablement visibility
GitHub Changelog · October 6, 2026 · Same story
- 5Anthropic launches free AI security scans for open-source
The Verge AI · October 8, 2026 · Background
Follow this story
Open the full story →GitHub adds AI Scan security metrics
3 developments
- Oct 13 · GitHub Changelog
GitHub adds AI Scan security metrics (This article) - Oct 15 · GitHub Changelog
GitHub AI Scan for PRs generally available↳ GitHub AI Scan is generally available for PHP, Shell, Terraform, and Dockerfiles with autofix suggestions. - Oct 23 · GitHub Changelog
GitHub Public Monitoring Adds Triage and API↳ GitHub Public Monitoring adds triage, API access, and webhooks for integration with incident response pipelines.
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