Tag: llm

Prompt-level defenses against injection are probabilistic and lose to a patient attacker. Here's the capability-level design that holds, with working configs.

Loading model weights, not math, is your GPU bottleneck. Continuous batching with llama-server serves many concurrent requests for close to the cost of one.

A 2026-09-22 patch left a self-hosted model's weights untouched but made it more confident on nonsense input. Six systems compared, real numbers only.

Jev, Von, and SemIf scored head to head on real commit history: a frozen 4B general model beat a purpose-built 395M decision model on every task tested.

I ran TypeSafe's Jev model against 840 blog posts to fix tag drift. Real cost numbers, benchmarked accuracy, and the failure mode that almost cost pageviews.

Komodo's community MCP server beats mounting the Docker socket or handing an AI agent SSH: scoped auth, per-tool RBAC, and confirmation before deletes.

Nano Banana's blurry images come from two causes: permanent generational loss from iterative editing, and a June 2026 outage Google fixed within 15 hours.

Coding agents write flawless code and leave hero.png blank. Compare self-hosted GPU image generation against subpixel, a ChatGPT-subscription CLI tool.

Aider offers interactive CLI-based pair programming with git awareness. Continue provides IDE-integrated AI assistance. Learn when to use each.

IDE-integrated AI coding with local LLMs. Set up Continue.dev + Ollama, pick models, configure chat & autocomplete, save money and keep code private.

Run embeddings on Postgres with pgvector. Skip Chroma/Qdrant, tune IVFFlat vs HNSW indexes, build RAG pipelines locally.

What is an AI harness? A plain-language answer, plus 21 of them grouped by job: Claude Code, Codex CLI, Kilo Code, Goose, OpenHands and DeepSeek Harness.