Starlog — Page 53
// LATEST
Cybersecurity
Inside GitHub's Secret Detection Engine: A Pattern Library for Catching Credentials in Code
Cybersecurity
Inside CVE-2024-22026: How a Simple CLI Wrapper Became Root's Worst Enemy
AI Agents
SCOUT-2: Building Multi-Persona AI Assistants Without Vendor Lock-In
Cybersecurity
Testing LLM Agents Without Losing Your Mind: Inside Giskard's Trace-Based Architecture
Automation
Proving WebAssembly Sandboxes Are Safe: When Formal Verification Meets Performance
AI Dev Tools
PII Detective: Why Scanning Column Names Beats Scanning Data for Privacy Compliance
LLM Engineering
LLM Canary: OWASP-Aligned Security Testing for Language Models
Developer Tools
Inside the Arsenal: A Taxonomy of Privacy Attacks Against Machine Learning Systems
LLM Engineering
ModelScan: Detecting Malicious Code in ML Models Before It Executes
Cybersecurity
Prowler: Building a Multi-Cloud Security Scanner That Maps Attack Paths
Data & Knowledge
Inside RAGET: How Giskard Automates RAG System Testing with Generated Test Cases
LLM Engineering
BIG-bench: Google's 200+ Task Gauntlet for Language Model Evaluation
AI Agents
Nerve: Building AI Agents as Infrastructure Code
LLM Engineering
OpenVLA: Training Vision-Language-Action Models That Actually Manipulate Objects
LLM Engineering
How a Single Adversarial Image Can Jailbreak Vision-Language Models
AI Dev Tools
DecodingTrust: The Eight-Dimensional Benchmark Exposing What GPT Models Hide
Cybersecurity
Inside China's Enterprise Vulnerability Knowledge Base: A Security Researcher's Guide to 0day404
AI Dev Tools
Building Claude Prompts That Actually Work: AWS's Meta-Prompt Engineering Tool
AI Dev Tools
AutoTemp: Multi-Armed Bandit Optimization for LLM Temperature Selection
AI Dev Tools
Mapping the Deepfake Landscape: A Technical Tour of Awesome-Deepfakes
AI Agents
STORM: Building Wikipedia-Style Reports Through Simulated Expert Conversations
Cybersecurity
SWE-agent: Teaching Language Models to Fix Bugs by Giving Them a Terminal
LLM Engineering
LaVague: Building Web Agents That Actually Understand What They're Doing
AI Agents