> your AI agent picks dependencies from memory; give it dated facts — try starlog.dev ↗ vet your agent's deps ↗ vibe-coding is fine. vibe-importing isn’t. — try starlog.dev ↗ vibe-importing isn’t fine ↗ your agent has never seen your private packages — try starlog.dev ↗ facts for private packages ↗ a linter for the dependencies your AI agent picks — try starlog.dev ↗ a linter for agent deps ↗ whois is redacted, cdns mask the rest — get the real operator — try whoisgeni.us ↗ who really runs that domain ↗ domain attribution that shows its work — full evidence chain — try whoisgeni.us ↗ domain intel w/ evidence ↗

← All articles

LLM Engineering

How LLM applications get built and shipped: inference and serving, structured output, token formats, evaluation, and the libraries powering production language-model systems.

168 articles

LLM Engineering

mergekit: Combining LLMs Without Training by Operating in Weight Space

★ 7.1k Python May 10, 2026
LLM Engineering

Building a Prompt Injection Firewall: Inside Vigil's Multi-Layer Defense System

★ 475 Python May 9, 2026
LLM Engineering

How GPT-2 Leaks Its Training Data: A Deep Dive into Language Model Memorization

★ 196 Python May 9, 2026
LLM Engineering

Inside Microsoft's Responsible AI Toolbox: A Widget Architecture for Model Accountability

★ 1.8k TypeScript May 9, 2026
LLM Engineering

LLM OSINT: When AI Becomes a Digital Private Investigator

★ 268 Python May 9, 2026
LLM Engineering

LLM Canary: OWASP-Aligned Security Testing for Language Models

★ 28 Python May 9, 2026
LLM Engineering

ModelScan: Detecting Malicious Code in ML Models Before It Executes

★ 697 Python May 9, 2026
LLM Engineering

BIG-bench: Google's 200+ Task Gauntlet for Language Model Evaluation

★ 3.2k Python May 9, 2026
LLM Engineering

OpenVLA: Training Vision-Language-Action Models That Actually Manipulate Objects

★ 6.1k Python May 9, 2026
LLM Engineering

How a Single Adversarial Image Can Jailbreak Vision-Language Models

★ 275 Python May 9, 2026
LLM Engineering

LaVague: Building Web Agents That Actually Understand What They're Doing

★ 6.3k Python May 9, 2026
LLM Engineering

Inside JailbreakHub: What 15,000 Real-World ChatGPT Exploits Reveal About LLM Security

★ 3.7k Jupyter Notebook May 9, 2026
LLM Engineering

Chain-of-Thought Reasoning for Any LLM in 150 Lines of PHP

★ 322 HTML May 9, 2026
LLM Engineering

Building a RAG System from Scratch: A 90-Minute Workshop Walkthrough

★ 4 Python May 9, 2026
LLM Engineering

Model Inversion Attack ToolBox: Benchmarking How Machine Learning Models Leak Training Data

★ 194 Python May 9, 2026
LLM Engineering

Haystack: Building Production LLM Applications Without the Black Box

★ 25.1k MDX May 9, 2026
LLM Engineering

Building Privacy-First File Organization with On-Device AI Models

★ 3.2k Python May 9, 2026
LLM Engineering

Broken Hill: Production GCG Attacks Against LLMs on Consumer Hardware

★ 161 Python May 9, 2026
LLM Engineering

MLX-VLM: Running Vision Language Models Locally on Apple Silicon Without the Cloud Tax

★ 4.7k Python May 9, 2026
LLM Engineering

AgentOps: The Missing Observability Layer for Production AI Agents

★ 5.5k Python May 9, 2026
LLM Engineering

Inside Inspect AI: How the UK Government Built a Framework for LLM Safety Evaluations

★ 2.0k Python May 9, 2026
LLM Engineering

E2B Desktop Sandbox: Building LLM Agents That Actually Control Computers

★ 1.4k Python May 9, 2026
LLM Engineering

Removing AI Safety Guardrails with a Single Vector: Inside Refusal Direction Research

★ 385 Python May 9, 2026
LLM Engineering

Building Production LLM Systems: A Deep Dive into the LLM Engineer's Handbook Reference Architecture

★ 5.0k Python May 9, 2026