Tech News
Show HN: Bullshit Detector – agent skills that fact-check videos and articles
A new open-source agent skill called Bullshit Detector fact-checks videos and articles using independent sources, sparking discussion on verification methods and tool adoption.
Anatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 Incident
Hugging Face just released this extremely detailed technical description of OpenAI's recent accidental cyberattack against their infrastructure.
Market surveillance agent with LangGraph and Strands on AgentCore
Learn how to architect and deploy a production-ready multi-agent AI system using LangGraph for workflow orchestration and Strands for agent reasoning on Amazon Bedrock AgentCore.
Scientific computing in the age of agentic AI
A new field report shows how scientists use AI coding agents to modernize scientific computing, accelerating software development and discovery in genomics and beyond.
Gemini API Managed Agents: 3.6 Flash, hooks, and more
Managed Agents Gemini 3.6 Flash, Hooks and Triggers.
GitHub Repos
Graphify-Labs/graphify
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph.
# Python# ai agents# antigravityruvnet/ruflo
🌊 The leading agent meta-harness.
# TypeScript# agentic ai# agentic frameworktrpc-group/trpc-agent-go
A Go framework for building production agent systems with graph workflows, tools, memory, A2A, AG-UI, MCP, evaluation, and observability.
# Go# a2a# a2a protocolResearch Papers
Temporal-Distance JEPA: Plan-Aware Representation Learning for Latent World Model Predictive Control
This paper proposes TD-JEPA, a method that learns temporal distance in representation space to improve planning in latent world models, outperforming prior JEPA-based planners on several simulated robotics tasks.
RSIBench-Data: Benchmarking Data-Centric Research for Recursive Self-Improvement
RSIBench-Data is a benchmark to test if LLM agents can automatically improve training data strategies for AI models, finding that current agents can make some discoveries but struggle to consistently improve.
Detecting Knowledge Inconsistencies Across Text, Tables, and Knowledge Graphs
Wikipedia and Wikidata are widely used for information access, LLM pre-training, and retrieval-augmented generation. Their knowledge is deeply connected but scattered across text, tables, and knowledge graphs.