» Tag
llm
536 postsLangGraph Pipelines Can Succeed and Still Be Wrong
LangGraph pipelines can finish cleanly while routing decisions silently drift wrong. See why maker/checker divergence and state snapshots catch what standard monitoring misses.
Local Motion Brings Local LLM Agents to Cursor and VS Code
Local Motion auto-picks a compatible local coding model on Mac, manages memory, and links to Cursor via tunnel or runs fully local inside VS Code.
Code or Diffusion: A Field Guide to Programmatic Image Generation
Generating diagrams and charts as code instead of diffusion cuts costs and produces testable, diffable, version-controlled image assets.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comaeovim: Orchestrating Claude Code agents like Neovim
aeovim is a Rust TUI that applies Neovim's modal, split-based workflow to LLM coding agents, letting developers orchestrate multiple Claude Code sessions from the keyboard.
Token Governor: The Smart Gateway That Cuts LLM Costs
Token Governor re-engineers LLM prompts to spend the fewest tokens needed, acting as a governing gateway that works with Anthropic, OpenAI, Gemini and any compatible provider.
Unified Memory: Why Mini PCs Run 70B Models a Big GPU Can't
Unified-memory mini PCs like AMD's Strix Halo can load 70B-parameter models that a $2,000 RTX 5090 cannot fit. Here's why capacity and bandwidth pull in opposite directions.
Scarf Moves From Haskell to Python in the AI Coding Era
Scarf explains why faster LLM-driven code generation made Haskell's long compile times and ecosystem friction unsustainable, prompting a move to Python.
RAG vs AI Agents: Understanding the Real Difference
RAG retrieves knowledge; AI agents plan and act. This piece breaks down the architectural differences and when to use each approach in production systems.
Cutting Claude API Costs 84% by Separating Vision and Reasoning
An OCR pipeline routed page images to Haiku and reasoning to Sonnet instead of Opus, cutting Claude API costs by 84%. Includes the model-routing math and a real JSON parsing bug.
Inside LLM 'private thoughts': J-Space isn't consciousness, it's control
Researchers spot J-Space, an internal workspace in transformers guiding reasoning. Not consciousness, but a practical clue for AI developers and safety.