Braintrust is using Codex, combined with GPT-5.5, to enhance their coding efficiency. This integration allows engineers to quickly convert customer requests into code, speeding up the development process. The use of AI in coding is becoming increasingly common, offering significant time savings and allowing developers to focus on more complex tasks. This move by Braintrust underscores the potential of AI tools in transforming software development workflows.
Read originalEarlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
The Verge AI · May 14, 2026 · Background
The Rundown AI · May 15, 2026 · Background
GitHub Changelog · May 18, 2026 · Background
The AI Daily Brief · May 18, 2026 · Background
OpenAI · May 20, 2026 · Related
WIRED AI · May 26, 2026 · Background
Cole Medin · May 28, 2026 · Background
Skill Leap AI · May 28, 2026 · Background
Duncan Rogoff · May 31, 2026 · Background
Cole Medin · June 15, 2026 · Background
TechCrunch AI · August 5, 2026 · Background
OpenAI · September 8, 2026 · Related
GitHub Changelog · September 22, 2026 · Background
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.
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.
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.