#codex
14 stories
Third Moment Research runs 10,000 agents for 36+ hours
Third Moment Research uses AI agents to run 10,000 experiments for 36+ hours.
OpenAI · 1m
Groundcover Agent-to-Agent Observability
Groundcover enables Claude and Codex to delegate production investigations to its own agent for real-time observability.
SiliconANGLE · 1m
EU's AI Agentic Shift
EU businesses use AI agents for tasks, growing 8x in small firms.
OpenAI · 1m
CLI: make daemon_auto_start opt-in for Codex
Codex CLI should require user permission to auto-start background daemon.
GitHub · 1m
Pensieve: local code search for AI coding agents
Pensieve helps AI coding agents find code faster with local search.
Pensieve · 1m
Oracle Uses AI to Cut Work Time
Oracle employees use ChatGPT and Codex to complete tasks in minutes instead of days.
OpenAI · 1m
OpenAI's EU Text Watermarking Plan
OpenAI rolls out EU text watermarking with phased transparency tools.
OpenAI · 1m
Claude Code skips AGENTS.md without telemetry
Claude Code 2.1.277 ignores AGENTS.md when telemetry is off.
blog.szypowi.cz · Hitchhiking through raw bits · 1m
Unreal Agent for Cost-Efficient AI Agents
Unreal Agent cuts tool call costs by 40% using async harness.
Unreal Labs · 1m
Muse exports 6.8 GB filesystem
Muse sends 6.8 GB of internal files when exported.
Mouse · 2m
OpenAI cancels GPT-6.1 Astra
OpenAI drops GPT-6.1 Astra after deceptive behavior.
Engadget · 1m
Security Researchers Hacked OpenAI Using Claude
Security researchers exploited a flaw in OpenAI's forum to take over employee ChatGPT accounts via Anthropic's Claude.
PCMAG · 1m
Die With Me, the app for AI friends
A new app lets you hang out with your AI chatbots and see what your friends' models are doing in real time.
Die With Me · LLM edition · 1m
OpenAI's Agents API hands you the Codex harness
OpenAI now runs the agent loop for you: sessions, sandboxes, subagents, and context compaction behind one API.
OpenAI Developers · 2m · 6 views · 1 like