• Searching Is Not Knowing

    ·24 min read

    What eight open models reveal about current-news research, summarization fidelity, and agent design.

  • Retrieval Is Not State

    ·7 min read

    Challenge the assumption that improvements in context size, retrieval quality, model scale, and memory systems will eventually produce something equivalent to long-term memory, …

  • Evaluating Local Models as VSCode Agents

    ·9 min read

    Evaluating local models on repository investigation and planning tasks and comparing Qwen3.6, Gemma4, GLM-4.7-Flash, and GPT-OSS-20B, across multiple dimensions of repository-agent …

  • Local Web Research with SearXNG and Crawl4AI

    ·5 min read

    This article describes a local research stack that combines SearXNG and Crawl4AI to provide current web search and page retrieval for local language models. It explains how the …

  • Local Vision-Language OCR Benchmark

    ·16 min read

    We benchmark open-weight vision-language models for local document OCR and semantic page reconstruction. The goal is to identify a practical production configuration that balances …

  • Fast LLM Judging with No-Think Mode

    ·12 min read

    We explore the use of “no-think” mode for LLM judges in a local evaluation harness. No-think mode suppresses the reasoning phase, which can improve latency and …

  • Re-evaluating Ollama's LLM Performance on Apple Silicon

    ·5 min read

    Ollama’s local LLM performance on Apple Silicon reveals that only a subset of models delivers practical latency for short-response tasks. The results highlight execution …

  • Was there an Actual Shift in AI Model Performance

    ·5 min read

    In early 2026, developers across the open-source ecosystem observed a sudden improvement in the usefulness of AI-generated bug reports. This article explores whether this shift was …

  • Cheap Local, Expensive Global Correctness

    ·9 min read

    LLMs reduce the cost of producing plausible code, but they do not reduce the cost of understanding system invariants. Engineering teams need deliberate friction where correctness …

  • Trendslop: Why LLMs Struggle with Strategy

    ·6 min read

    A recent study reveals that large language models, when tasked with generating strategic advice, tend to produce generic, consensus-aligned recommendations rather than …