> 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

DITING: The LLM-Orchestrated Pentest Platform That Chose Workflows Over Autonomy

★ 125 Go Nov 16, 2026
LLM Engineering

MLX-VLM: Running Vision-Language Models on Apple Silicon With Production-Grade Inference

★ 5.8k Python Nov 3, 2026
LLM Engineering

Cyber Defense Benchmark: Testing Whether LLMs Can Hunt Threats with SQL

★ 13 Python Oct 30, 2026
LLM Engineering

DecBench: Measuring Decompilation Quality by Recompiling the Output

★ 132 Python Oct 30, 2026
LLM Engineering

Ollama: The Docker-Inspired LLM Server That Made llama.cpp Accessible

★ 185.3k Go Oct 30, 2026
LLM Engineering

Weightless: Runtime Activation Steering for LLMs Without Redistributing 100GB Checkpoints

★ 117 Python Oct 30, 2026
LLM Engineering

Building an LLM Server That Responds to DNS Queries: A Deep Dive into Protocol Abuse

★ 10 Rust Oct 21, 2026
LLM Engineering

FreeLLMAPI: A 7.4-Billion-Token Proxy That Aggregates 34 Free LLM Providers Behind One Endpoint

★ 34.9k TypeScript Oct 14, 2026
LLM Engineering

Surgical Model Modification: How Blackfrost's DWM Rewrites LLM Behavior Without Breaking Intelligence

★ 12 Python Oct 10, 2026
LLM Engineering

τ-Bench: The First Benchmark Where the User Fights Back

★ 2.2k Python Oct 10, 2026
LLM Engineering

AutoHarness: Teaching Claude Code to Remember What It Learned Yesterday

★ 9.2k Python Oct 8, 2026
LLM Engineering

HyperQwen: 1,000 tok/s on a Single RTX 3090 Through Aggressive Recurrent-State Speculation

★ 1.4k Python Sep 17, 2026
LLM Engineering

oMLX: Why This Mac Inference Server Caches to Your SSD (And Why That's Brilliant)

★ 21.7k Python Sep 14, 2026
LLM Engineering

Qwen3.8-27B on a Single RTX 3090: How Calibrated Quantization and Speculative Decoding Hit 1,000 tok/s

★ 1.2k Python Sep 8, 2026
LLM Engineering

METATRON: Building a Penetration Testing Assistant with Local LLMs and Zero Cloud Dependencies

★ 3.6k Python Aug 24, 2026
LLM Engineering

Switchyard: Composable LLM Routing Without the Gateway Lock-In

★ 1.2k Rust Aug 13, 2026
LLM Engineering

Running a 2.78-Trillion-Parameter Model on a Laptop: Inside WASTE's NVMe-Streaming Architecture

★ 2.0k C Aug 10, 2026
LLM Engineering

Running 35B MoE Models on 8GB GPUs: How vvllm-ms Caches Experts in System RAM

★ 1 Python Aug 8, 2026
LLM Engineering

Terminal-Bench: Why Evaluating LLM Agents on Real Terminal Tasks Is Harder Than You Think

★ 2.5k Python Aug 6, 2026
LLM Engineering

OSWorld-V2: The GUI Agent Benchmark That Hides Its Answers

★ 229 Python Aug 5, 2026
LLM Engineering

Running a 2.78-Trillion-Parameter Model on a Laptop: Inside WASTE's NVMe-Streaming Engine

★ 145 C Jul 31, 2026
LLM Engineering

Running 753B MoE Models on Consumer GPUs: Hand-Written SASS Kernels for 2-Bit Experts

★ 253 Sass Jul 10, 2026
LLM Engineering

LLM Checker: Hardware-Aware Model Selection for Local Inference

★ 2.8k JavaScript Jun 29, 2026
LLM Engineering

Fighting LLM Hallucinations in 2026: llm-council vs claude-octopus vs LLM-Check

Various Jun 22, 2026