Long horizon tasks with Codexkept by eddie • feb 24OpenAI's Codex successfully built a design tool from scratch over 25 hours, demonstrating long-horizon agentic coding with milestone-based planning and continuous verification.AboutMETR · OpenAI · Codex · Cursor · GPT-5-CodexFiled#ai-agents#ai-coding#developer-tools#productivity#software-engineeringRelatedBuilding an AI-Native Engineering TeamCoding agents like Codex can now sustain multi-hour reasoning tasks, transforming the entire software development lifecycle by delegating mechanical work across planning, design, build, test, review, and deployment.also on METR, Codex, OpenAI, #ai-coding, #software-engineering, #developer-toolsWe are Changing our Developer Productivity Experiment Design - METRMETR’s late 2025 experiment on AI developer productivity suffers from selection bias because many developers refuse to work without AI, yielding unreliable speedup estimates.also on METR, Codex, #ai-agents, #ai-coding, #software-engineering, #productivity, #developer-tools