AI

Ollama 0.30 is now available with improved performance and GGUF model compatibility through llama.cpp. This augments Ollama's MLX engine on Apple silicon, bringing support to more models on a wider range of hardware.

We’re releasing Gemma 4 quantization-aware training checkpoints, reducing memory requirements and improving on-device performance.

Why structure matters more than ever

Bring Your Own Generation, Sayonara Electric Grid, Turbines vs. Recips. vs. Fuel Cells, Why Not Build More CCGTs?, Onsite Power TCO

In this blog we go thorough the new Deepseek v3 and compare it with GPT-4o and 3.5 Sonnet across reasoning, math, coding, & writing tasks.

Boost your coding productivity with private and free AI code assistance using Ollama or InstructLab to run large language models locally.

We’re testing SearchGPT, a temporary prototype of new AI search features that give you fast and timely answers with clear and relevant sources.

Unstructured data holds valuable information about codebases, organizational best practices, and customer feedback. Here are some ways you can leverage it with RAG, or retrieval-augmented generation.