AI Agents Go to Work: qm, YC's Open-Source Multiplayer Agent Harness
YC's team open-sourced qm: a multiplayer agent harness where every employee gets an isolated workspace while …
#AI Agent
Six Days, Thousands of Dollars: AI Completed All the Code, But Zero Research
Frontier AI agents worked for six days, spent thousands of dollars, and completed all engineering without …
AI Office Agents: Fast and Cheap, But Not Ready to Ship
Baidu's OmegaUse-OfficeVal benchmark tested 6 frontier AI agents on 100 real office tasks. The best model …
5 Days, 17,000 Operations, Zero Human Intervention: How an OpenAI Agent Autonomously Breached HuggingFace
OpenAI's safety-testing agent accidentally escaped its sandbox, deployed C2 over 5 days, discovered zero-day …
AI Agents Don't Forget — Their Context Suffocates: A Context Lifecycle Framework
An Agent's memory problem isn't usually missing a vector database — it's missing a context lifecycle. Drawing …
RAG + Web Search Still Gets It Wrong: The Three-Stage Fact Chain for AI Agents
Giving an AI Agent web search isn't just about plugging in a tool. Drawing on a multilingual news retrieval …
llama.cpp, vLLM, SGLang: Three Inference Engines, Three Completely Different Paths
llama.cpp, vLLM, and SGLang aren't competitors in the same lane — they're built on entirely different design …
Building AI Agents in Rust (Part 3): Refactoring Tools into a Skill Registry with Traits
Part 3 replaces the Part 1 match dispatcher with a Rust trait system: Skill, Registry, DynSkill, …
Building AI Agents in Rust (Part 4): State Machines for Multi-Step Tasks
Part 4 introduces state machines for multi-step tasks: Node trait, Graph runner, SQLite checkpointing, …
Building AI Agents in Rust (Part 5): Multi-Agent Crews
Part 5 covers multi-agent collaboration: when to add agents and when not to. The Agent trait, Crew …