Starlog — Page 61
// LATEST
AI Agents
HADES: Training Blue Teams with AI-Powered Adversaries That Never Sleep
Cybersecurity
Building Explainable Offensive Security with Agentic AI: A Deep Dive into Multi-Agent Reconnaissance
AI Agents
Strands Agents: Building AI Agents with Decorators and Model Context Protocol
LLM Engineering
Unsloth: How Custom Triton Kernels Make LLM Fine-Tuning Possible on Consumer GPUs
AI Agents
Building Agents That Build Themselves: Inside Meta-Tools-and-Agents
AI Agents
Building Multi-Agent Orchestration on AWS: Inside Omnimesh's Gateway Pattern
AI Agents
Amazon Nova Act: AI Agents That Actually Navigate the Web Without Breaking
AI Agents
Strands Agents Tools: Building Multi-Agent Systems Without Reinventing the Wheel
AI Agents
PenGym: Training Reinforcement Learning Agents Against Real Vulnerable Systems
AI Dev Tools
DeepSeek-OCR: Rethinking Vision Encoders as Extreme Compression Engines
AI Agents
CodeMachine: Turning AI Coding Assistants Into Orchestrated Workflows
AI Agents
GPTSwarm: Building Self-Optimizing Agent Networks with Reinforcement Learning
AI Agents
Inside HGM: A Self-Rewriting AI That Improves Its Own Code
AI Agents
AutoAgents: Dynamic Multi-Agent Generation for GPT-4 Orchestration
AI Agents
Tongyi DeepResearch: The First Open-Source MoE Agent Built for Multi-Step Research
Cybersecurity
Strix: AI Agents That Actually Hack Your Code (And Prove It)
Cybersecurity
SecPipe: Teaching AI Agents to Chain Security Tools Like Expert Researchers
LLM Engineering
TOON: The Data Format That Makes LLMs Pay Attention to Your Tables
Developer Tools
BountyBench: A Framework for Benchmarking AI Agents on Security Vulnerability Research
AI Agents
Inside the Framework Measuring How Good AI Agents Are at Hacking
AI Agents
WASP: The Security Benchmark That Catches What Your Web Agent Misses
AI Agents
Web-Shepherd: Training Web Agents with Process Rewards Instead of Binary Success
AI Agents
GUARDIAN: Detecting When Your AI Agents Start Lying to Each Other
AI Agents