Brendan McKeag

Runpod now supports secure internal communication between pods across data centers. With Global Networking enabled, your pods can talk to each other privately via .runpod.internal—no open ports required.

Runpod now supports scoped API keys with per-endpoint access, usage tracking, and on/off toggles. Create safer, more flexible keys that align with the principle of least privilege.

Explore how Code in a Jiffy built a fully functional AI-powered coffee shop chatbot using Runpod. This community spotlight covers agentic chatbot structures, full-stack architecture, and how Runpod’s serverless infra simplifies deployment.

Stable Diffusion 3.5 delivers a major quality leap, fixing past flaws while generating photorealistic images from minimal prompts. Learn what’s new, how to get started on Runpod, and what to expect next from the community.

NVidia’s Llama 3.1 Nemotron 70B is outperforming larger and closed models on key reasoning tasks. In this post, Brendan tests it against a long-unsolved challenge: consistent, in-character roleplay with zero internal monologue or user coercion—and finds it finally up to the task.

Large language models can write poetry and solve logic puzzles—but fail at tasks like counting letters or doing math. Here’s why, and what it tells us about their design.

Lower VRAM usage and improve inference speed using GGUF quantized models in KoboldCPP with just a few environment variables.