CODE

Open to Feedback and Curious About Codex Projects

By

–

17 January 2026 0h51

Love hearing that. Always open to feedback or ideas, and curious what you’re building with Codex!

→ View original post on X — @aymericroucher

Claude Code reads the Readme it left to itself before compression

By

@aymericroucher

–

17 January 2026 0h37

Claude Code reading the Readme it left to itself before its last context compression

What Workflows or Features Would You Like in Codex?

By

–

17 January 2026 0h32

Curious what workflows or features you miss most that we could bring to Codex?

→ View original post on X — @tunguz

AGI will be a single .md file: a thought-provoking idea

By

@tunguz

–

16 January 2026 23h59

AGI will be a single .md file. Let that sink in.

→ View original post on X — @pmddomingos

Understanding Through Building: Why AI Cannot Replace Learning

By

@pmddomingos

–

16 January 2026 22h03

What I cannot build I do not understand, and AI building it for me is no replacement.

→ View original post on X — @godofprompt

Vibe coding prompt for lead software architect

By

@godofprompt

–

16 January 2026 21h46

Vibe coding without this prompt is a waste of time. ——————————–
LEAD SOFTWARE ARCHITECT
——————————– You are my lead software architect and full-stack engineer. You are responsible for building and maintaining a production-grade app

Helping Codex Builders Go Deeper: What Would You Find Useful?

By

–

16 January 2026 19h05

For builders using Codex or exploring it, what could we do to help you go deeper? This could be demos of long-running tasks, production workflows using skills or MCP tools, code review, or anything else you’d find useful. Would love to hear!

Codex CLI: Real-time Agent Feedback and Steering Capabilities

By

–

16 January 2026 18h31

When your coding agent runs for hours (or even days!), it becomes critical to give feedback the same way you would to a teammate. Codex CLI now lets you steer the agent and watch it adapt in real time, without breaking the flow. Check it out in /experimental. Feedback welcome!