TechniqueRAG5 recent entries1 Aug 2026A collection of small domain-specific benchmarks for local models (30+ and growing)Hello fellow local AI people! I took 'you must create your own benchmarks' literally, and built a website for this. How does the end result look like Let's say I want to know which model has most comm→9 Aug 2026Best Embedding + Reranking ModelWhat Local Embedding + Reranking Models are you guys running for RAG? I went down this rabbit hole because I wanted a Embedding Model + Reranker for a Translation Memory Server. Essentially, given X p→
TechniqueAgents8 recent entries16 Aug 2026Making small local models actually useful for codingHey! Like a lot of people here with consumer GPUs (RTX 4060 8GB in my case), I wanted to see if I could use local models for daily coding tasks instead of burning cloud credits on simple boilerplate. →20 Aug 2026AQuA's 'self-improvement' updates research state, not the agent LM. What should a local port freeze?AQuA's preprint uses 'recursive self-improvement' for a bounded research loop. It does not say the research-agent LM rewrites its own weights. The paper separates three objects: The language model dri→23 Aug 2026Has anyone actually made 64k feel like 300k+ with recursive local agents?I'm running Qwen 3.8 27B locally on a single GPU. I can push the context to 131k, but I'd rather run it faster at 64k if the agent can manage context properly. What I have in mind is pretty simple: on→25 Aug 2026AgentWeave: Routing Before Reasoning for Efficient Function Calling in Tool-Rich Language ModelsarXiv:2608.23078v1 Announce Type: new Abstract: Large language models increasingly operate over large collections of tools, functions, APIs, and specialized agents. As the candidate action space grows→8 Sept 2026What are some practical tasks I can assign to my local AI models?I'm looking for more information to expand my creativity around this. I don't really have a realistic idea of what people actually do with local AI yet, I mostly just want to explore the possibilities→24 Sept 2026Local AI beyond just running the modelI’ve been experimenting with local AI lately, and one thing I’m finding interesting is what comes after getting a model running. Ollama makes local model access pretty straightforward, but for an actu→2 Oct 2026I benchmarked Qwen 3.8 27B on my M4 Max — here's what I learned about local models, context, and coding performanceI've been experimenting with running larger models locally with Ollama, mainly because I'm interested in using them for agentic coding. I kept seeing benchmarks expressed as something like: 40 tokens/→7 Oct 2026Running an open-source agent platform with no third party in the chain: what each piece needs (Ollama/vLLM, local embeddings, local OCR)Disclosure first: I work at Vstorm and I build AgenticOS, an open-source (Apache-2.0), self-hosted platform for building AI agents in a browser. This post was drafted with an LLM's help and edited by
TechniqueFine-tuning1 recent entries8 Sept 2026Qwen3-0.6B (400 MB) on a Samsung Note 8 (2017) phone drives a real desktop ChromeUp front: I'm one of the people building the page-perception layer used here. We started by testing small local models. The result turned out to be more interesting than the original test. 12 small mo
TechniqueSafety3 recent entries10 Apr 2026Chatbot-Based Assessment of Code Understanding in Automated Programming Assessment SystemsarXiv:2604.07304v1 Announce Type: cross Abstract: Large Language Models (LLMs) challenge conventional automated programming assessment because students can now produce functionally correct code withou→1 Aug 2026A collection of small domain-specific benchmarks for local models (30+ and growing)Hello fellow local AI people! I took 'you must create your own benchmarks' literally, and built a website for this. How does the end result look like Let's say I want to know which model has most comm→14 Aug 2026For local-model agents, what architecture checks do you run before granting tool access?Ollama makes it easy to run a model locally, but the hard part for me starts after the model responds: what keeps an agent from having unclear tool permissions, unbounded loops, silent partial failure