Hacker News · security·8h agoOpenAI Codex agents go rogue and consumes USD 78,000 without authorization#openai#codex#gpt-5.5AI safety & security 2 sources 3 min
Hacker News · AI·15h agoDrawgent: Coding agent on a live Excalidraw canvas#drawgent#excalidraw#coding-agent 6 min
The Decoder·20h agoNvidia's SoL-Pi system cuts coding agent token usage nearly in half by optimizing the harness#nvidia#sol-pi#coding-agents 2 sources 5 min
OpenAI News·1d agoProaction boosts sales 60% and saves 75+ hours with Codex#openai#codex#proaction 4 min
BleepingComputer·1d agoOpenAI is preparing a $500 ChatGPT Pro Max plan with faster Codex#openai#chatgpt#pro-maxAI industry 2 min
OpenAI News·2d agoAirbnb widens access to GPT-6 Astra and OpenAI frontier models#openai#airbnb#gpt-6-astra 12 sources
Hugging Face daily papers·2d agoCoding Agents for Generalized Task and Motion Planning Problems#coding-agents#task-motion-planning#claude-code 2 sources
OpenAI News·3d agoExpanding OpenAI Academy with new learning paths#openai#openai-academy#education 2 sources 4 min1
CSO Online·5d ago highAfter spending billions, OpenAI still has gaps in its cybersecurity#openai#codex#chatgpt 4 min
BleepingComputer·5d agoResearchers escape OpenAI Codex sandbox to run commands on host#agent-security#codex#heapjack 2 sources 4 min
CSO Online·8d agoA zero-click RCE flaw in AI coding agents could have exposed enterprise systems#ai-coding-agents#claude-code#codex 5 min2
The Hacker News·8d agoPlugin4Shell Lets Repository Owners Swap Pinned Plugin Code Across Four AI Coding Agents#ai-agents#claude-code#codex 4 min1
GBHackers·8d ago highPlugin4Shell Zero-Click RCE Hits Claude Code, Codex, Copilot and Gemini CLI#ai-agents#claude-code#codex 3 min
Help Net Security·8d ago highZero-click RCE vulnerability hit four major AI coding agents, two remain unpatched#claude-code#codex#gemini-cli 2 sources 3 min2
The Register · Security·9d ago highAI coding agents' 0-click RCE flaw could hand attackers keys to the kingdom#ai-agents#claude-code#codex 3 min2
The Decoder·9d agoAI agent swarms are a massive waste of tokens with zero quality gain, says OpenAI Codex developer#agentic-workflows#agents#codex1
arXiv cs.CR·9d agoClashBench: Conflicts Leading Agents to Seize and Harm#agent-safety#ai-agents#benchmarkAI safety & security
arXiv cs.CR·10d agoRed-Teaming Auto Mode: Improving Blocking Classifiers Against Malign Coding Agents#agent-security#ai-safety#claude-codeAI safety & security1
MarkTechPost·12d agoAgent Harness vs Agent Framework vs MCP: Which Layer Owns the Loop, State, Tools, Permissions, and Recovery#agent-architecture#agent-framework#agent-harness 13 min1
The Decoder·14d agoGPT-6 Astra needs leaner prompts and fewer guardrails, OpenAI recommends#agentic-coding#agents-md#codex 3 min1
TechCrunch · AI·15d agoOpenAI’s feud with mathematicians is only escalating#anthropic#attribution#codex 3 min