» Tag
llm
535 postsAnatomy of a Full Self-Hosted RAG Stack, End to End
A self-hosted RAG pipeline in full: Docling parsing, dual dense/sparse indexing, RRF hybrid search, knowledge graphs, token budgeting, and parallel ingestion.
Orchestrated Agents Over One Prompt: Lessons From a Branding Platform
BrandBrahma's team explains why they chose a four-orchestrator agent architecture over a single LLM call, separating verification tasks from generative ones for reliability.
MiniMax M2.7: Open-Source AI That Optimized Its Own Training
MiniMax's open-source M2.7 model actively shaped its own training via memory writes and skill-building, gaining 30% efficiency and matching GPT-5.3-Codex on SWE-bench Pro.
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.comBuilding an AI that pentests your AI, with proof required
An engineer built an adversarial LLM harness that only reports proven exploits against a live agent, replacing vague 'might be vulnerable' pentest reports with deterministic, oracle-verified findings.
Claude's Weights Are Closed, So a Live Thought Viewer for Qwen
Inspired by Anthropic's workspace paper, a developer built a live, token-level inner-thought viewer for the open Qwen model since Claude's weights are closed.
When AI Reviewers Disagree: A Multi-Agent Code Review Tribunal
ShiftLeft Society pits two AI reviewers against each other in a cost-based negotiation, using Qwen-Max to cut false positives and raise accuracy from 82.5% to 95%.
UAP: An Open Ad Protocol That Can't Touch LLM Answers
UAP is an open, vendor-neutral protocol letting any LLM provider sell ads without altering answers or leaking conversation context.
Shoehorn: Rust Tool Quantizes LLMs to Fit Your Mac's Exact VRAM
Shoehorn is a Rust CLI that quantizes BF16 GGUF LLMs per-tensor to exactly fit your Mac's available VRAM, maximizing quality under a hard memory budget.
Agentic AI Economics: Why Unconstrained Autonomy Costs More
Agentic AI deployments are overspending and creating security holes by treating rigid business workflows as open-ended reasoning tasks.
Moonshot's 2.8T-Parameter Kimi K3 Runs on a GPU-less Mini PC
A 2.8T-parameter open-weight Kimi K3 model ran on a GPU-less mini PC using disk-streamed MoE experts and native MXFP4 quantization.