@reach_vb - AI Dynamics - Page 38 of 103

Codex CLI and Extension both support Web Search by default now! No need to explicitly pass the “search” flag anymore. By default codex will use web search cache except when using full access sandbox (or yolo) where it’ll default to live! So nice to finally see this live!

→ View original post on X — @reach_vb

29 January 2026

Using AI coding assistant to manage code changes

By

@reach_vb

–

29 January 2026 1h07

I just ask codex to remove the changes I don’t want and it works like magic

→ View original post on X — @reach_vb

29 January 2026

Practical AI-Driven Coding Workflow and Tooling Setup

By

@reach_vb

–

28 January 2026 22h12

pretty happy with my current coding setup: – gpt-5.2-codex
– xhigh for planning
– medium for implementation
– background terminal (parallel jobs)
– /fork conversations to explore multiple variations of a problem
– codex web via slack for quick async validation/ simple changes
–

→ View original post on X — @reach_vb

28 January 2026

Using AI to fetch and manage documentation

By

@reach_vb

–

26 January 2026 16h59

thanks for the details! for docs my go-to is to just ask codex to fetch the latest instead of providing it myself

→ View original post on X — @reach_vb

26 January 2026

OpenAI’s reliance on Codex for internal tooling and rapid development

By

@reach_vb

–

25 January 2026 8h41

Can confirm – we made the OpenAI MCP server in ~3 days (and scale proof), there’s Sora android app in ~3 weeks and a lot more internal tooling built by codex, reviewed by codex. Hard to see how OpenAI could still ship at the speed it does without codex. Anecdotally, I spend a

→ View original post on X — @reach_vb

25 January 2026