Search results 8 items matching your search terms. Filter the results Item type Select All/None Collection File Folder Image Note Page New items since Yesterday Last week Last month Ever Sort by relevance date (newest first) alphabetically AI Augmented Investigative Journalism by kaeru — published Jul 20, 2025 — last modified Aug 14, 2025 01:12 PM — filed under: anticorruption, rocm, investigative journalism, AI, docling, lighrag, open-webui Initial explorations in using current AI tools and methods to supplement existing investigative journalism techniques Located in Notes Local AI Assisted Development with OpenCode, Qwen 3.6 and llama.cpp by kaeru — published Apr 24, 2026 — last modified Aug 25, 2026 02:43 PM — filed under: rocm, AI, opencode, plone, darktable With release of Qwen 3.6 35B A3B, AI assisted development is now useful on local setup with limited VRAM. Located in Notes Processing Scanned Documents with AI by kaeru — published Aug 14, 2025 — last modified Aug 15, 2025 06:08 AM — filed under: AI, VLM, docling Older document processing methods still need to be used in conjunction with current AI Visual Language Models (VLMS) when dealing with badly scanned documents. Located in Notes RAG with newer 30B models, Google Pinpoint and VLMs by kaeru — published Oct 26, 2025 — last modified Oct 28, 2025 02:51 AM — filed under: VLM, AI, investigative journalism, darktable, lua, google LightRAG with Qwen3 30B Thinking model, Google Pinpoint and VLMs to speed up journalism workflows Located in Notes Cleaning up Documents with VLMs by kaeru — published Dec 02, 2025 — last modified Dec 27, 2025 04:00 AM — filed under: AI, VLM, 1MDB, anticorruption Cleaning up documents, this time with VLMs and AI generated one off scripts Located in Notes Querying Federation of Malaya Budget from 1959 by kaeru — published Dec 05, 2025 — last modified Dec 05, 2025 02:09 PM — filed under: VLM, AI, govdocs Current state of VLMs allows us to query accurately printed tables from the late 1950's Located in Notes Local AI with AMD Radeon 9070 XT on Ubuntu Linux 25.04 with ROCm 6.4.1 by kaeru — published Jul 06, 2025 — last modified Aug 14, 2025 01:14 PM — filed under: AI, rocm, ubuntu, ollama, llamacpp, vllm, docling Everything seems to be working so far Located in Notes ROCm and Vulkan on Ubuntu VM on FreeBSD with Bhyve GPU Passthrough by kaeru — published May 05, 2026 — last modified Aug 25, 2026 02:42 PM — filed under: freebsd, ubuntu, AI, rocm, vulkan, llama.cpp, bhyve With FreeBSD 15 and bhyve hypervisor you can can run and serve GPU powered local AI and compute services such as llama.cpp using ROCm and Vulkan with AMD GPUs ... Located in Notes Subscribe to an always-updated RSS feed.