pgvector for Local Embeddings
Run embeddings on Postgres with pgvector. Skip Chroma/Qdrant, tune IVFFlat vs HNSW indexes, build RAG pipelines locally.
Tag: llm
All the articles with the tag "llm".
What Is an AI Harness?
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.
The Free Tier Rug Pull
Free AI tiers are loans against a future price, paid in your data, your architecture, or your time. Here's the collateral to check before you build on one.
API vs Self-Hosted LLMs: The Real Cost
API vs self-hosted LLM cost reality, GPU TCO, privacy, latency, break-even math. When paying OpenAI/Anthropic wins. When local wins.
RAG Beyond Vector Search: BM25, Hybrid, Re-ranking
RAG beyond dense embeddings: BM25 lexical search, hybrid retrieval (RRF, weighted fusion), cross-encoder re-rankers (BGE, Cohere, Jina). When pure vector search fails.
How to Stretch a Free LLM Tier
Free LLM tiers usually die from bloated prompts, not stingy quotas. Context discipline, caching, tiering, batching, and backoff that triple your runway.
The Free AI Stack: What $0 Gets You
A capability map of what's free from AI providers in 2026: chat, APIs, image generation, speech tools, and coding help, with the real quotas.
Agentic Browsers: Browser-Use & Skyvern Reviewed
Browser-Use and Skyvern let LLMs drive real browsers via natural language goals. Here's what they can actually do, where they break, and when Playwright is still the right call.
Llamafile: Single-Binary LLMs That Actually Just Run
Llamafile bundles llama.cpp + Cosmopolitan libc into one portable binary that runs on Linux, macOS, Windows, and BSD with zero install.
DeepSeek V4 Flash: 28 Cents a Million
DeepSeek V4 Flash 0731 hits 50 on the independent intelligence index at $0.14/$0.28 per million tokens. Same weights as the preview, redone post-training.
DIY Perplexity: SearXNG + Local LLM = Private Web Search
Replace Perplexity with SearXNG + a local LLM for private, cited web search. Full Perplexica/Morphic deploy walkthrough, Ollama, latency tradeoffs.
Local Coding Agents Need Less Context
Local coding agents don't fail because your 27B model is too small. They fail because you let 200K tokens of garbage pile up in the context window. Cap it low.