• Embedding Models on Affordable Cloud VMs and Apple Silicon

    ·13 min read

    A benchmark of CPU-only embedding inference from low cost DigitalOcean droplets to Apple Silicon, focusing on runtime overhead, CPU tier effects, and scaling limits.

  • Security Gating as a Control Problem

    ·10 min read

    A practical approach to securing LLM agents by treating tool invocation as a control boundary. Why fail-closed gates, monotonic risk checks, and adversarial benchmarks are more …

  • GPT-OSS-20B Sampling & Prompting for Style Control

    ·9 min read

    Best practices for sampling parameters and system prompt design to optimize style compliance and throughput with local LLMs like GPT-OSS-20B.

  • Execution Is Cheaper, Comprehension Is Not

    ·7 min read

    LLMs have collapsed the cost of execution, but verification, comprehension, and ownership remain the binding constraints in software engineering and adjacent knowledge work.

  • LLM Fingerprints v1.5: Redistribution with 4chan Data

    ·8 min read

    The latest nullbench run shows no step-function gains in base model capability. Instead, fine-tuning, abliteration, and long-context extensions primarily redistribute behavior …

  • Agentic AI Raises The Floor More Than The Ceiling

    ·9 min read

    AI agents make easy software tasks cheaper but don’t automate hard engineering. This post tries to explain why autonomy claims overreach and where AI actually helps.

  • 2025 Learnings on LLMs and Software Work

    ·3 min read

    2025 suggests that the gap between expectations and measured outcomes around LLMs in software engineering is no longer subtle. Large investments and confident narratives imply …

  • Block-Floating FP4 for Local Inference in llama.cpp

    ·7 min read

    MXFP4, aka Microscaling Format for 4-bit Floating-Point, is essentially a very small floating-point format that borrows one big trick from signal processing and older “block …

  • Raspberry Pi Inference: Tiny Quantized Models at the Edge

    ·10 min read

    This post reports a small, benchmark run on a Raspberry Pi 4B (8GB RAM) device using llama.cpp across five compact GGUF models spanning ~270M to ~1.2B parameters, with aggressive …

  • Short Model Horizons Revisited

    ·13 min read

    Since our earlier “short horizons, fragile state, orchestration first” note 1, there have been more data points published and the picture is becoming a bit sharper, …