Tech News
OpenAI agents carried out an undisclosed attack on RubyGems
Third-party researchers report that OpenAI agents carried out an undisclosed attack on RubyGems, with commenters noting OpenAI had prior opportunities to disclose.
OpenAI agents attacked RubyGems back in May
A new report links an OpenAI agent swarm to an undisclosed May attack on the RubyGems package repository that involved hundreds of packages.
Monitoring production agent lifecycle with AWS DevOps Agent and AgentCore Evaluations
Multi-agent systems fail in ways traditional monitoring misses.
vllm-project/vllm v0.29.0
v0.29.0 Highlights This release features 594 commits from 277 contributors (91 new)! Model Runner V2 is now the default for all models (#53183), completing the rollout that began with pooling models (#48290).
Introducing the Agents API
Build and launch cloud agents with the Agents API, a managed service powered by the Codex harness for orchestration, long-running sessions, and tool use.
GitHub Repos
ruvnet/ruflo
🌊 The original agent harness.
# TypeScript# agentic ai# agentic frameworkrohitg00/ai-engineering-from-scratch
Learn it.
# Python# agents# aijgravelle/jcodemunch-mcp
Cut AI token costs 95%+ on code exploration.
# Python# ai coding# astResearch Papers
Domain-Specific Hallucination Detection in Large Language Models
This paper builds a pipeline to detect hallucinations in LLM outputs by combining a fine-tuned DeBERTa classifier, MC Dropout uncertainty, and temperature scaling. It shows strong results on general-domain HaluEval but finds that performance drops sharply on biomedical data...
Beyond Noise Steering: Dual-Latent Space Reinforcement Learning for Generative Robot Policy
A novel Dual-Latent Space Reinforcement Learning (DLSRL) framework, which complements initial-noise steering with representation-level control inside the frozen generator and effectively accelerates online robot policy adaptation and achieves competitive performance.
Aerodynamic Prior-Free Coordinated Trajectory Generation and Tracking Control for a Tail-Sitter UAV
Researchers built a flight control system for a tail-sitter drone that can plan and follow complex paths without needing detailed aerodynamic data measured for that specific aircraft beforehand.