doyaken.ai

Hacker News Claude Code · August 18, 2026 22:10

GitHub - gmhoward9289-ops/roost: top for Claude Code - live sessions, models, context, and the subagents they spawn

top for Claude Code - live sessions, models, context, and the subagents they spawn - gmhoward9289-ops/roost

Topics: Code Assistants

Entities: Code AssistantsClaudeClaude Code

Hacker News Claude Code · August 18, 2026 21:53

When deny doesn't win

Claude Code's fixed permission precedence has no way to express every narrow exception. Learn how permcheck uses containment-based carve-outs, and where its protection ends.

Topics: Code Assistants

Entities: Code AssistantsClaudeClaude Code

Planet AI Developer Filter · August 18, 2026 21:49

NVIDIA Releases TensorRT Model Connect in Public Preview: Hugging Face Checkpoint to Native C++ Inference in Two Commands

NVIDIA released TensorRT Model Connect in public preview, taking Hugging Face checkpoints to native C++ TensorRT inference without ONNX

Entities: NVIDIA

Planet AI Developer Filter · August 18, 2026 21:41

Frontier Model Cost and Open-Weights Popularity is Driving Demand for Model Routing

Glean CEO Arvind Jain explains why model routing helps control AI costs for organizations, and how human feedback loops at scale improve its routing systems.

Hacker News Claude Code · August 18, 2026 21:14

Teaching macOS to print to the HP Laser 1008a

The (lightly redacted) Claude Code session that gave a driverless HP Laser 1008a a native macOS driver — rendered in the Claude Code interface.

Topics: Code Assistants

Entities: Code AssistantsClaudeClaude Code

Hacker News Claude Code · August 18, 2026 20:14

ClaudeDevs (@ClaudeDevs) on X

We’re extending the 50% increase to weekly Claude Code limits through August 31. We hope to make this a permanent change to our plans, but strong demand for our models means that capacity may be tight over the coming weeks. We’ll keep you posted as things...

Topics: Code Assistants

Entities: Code AssistantsClaudeClaude Code