The Neuron: AI Explained BONUS: OpenAI Codex Demo, Learn the Absolute Basics of Coding with AI
9 snips
Feb 13, 2026 
Alexander Embiricos, product lead for OpenAI Codex who builds agentic coding tools, demos GPT-5.1 Codex Max live. He shows where Codex runs, how it executes safe terminal actions, and how teams customize agents and workflows. Demos include installing IDE extensions, scaffolding projects, making live code edits, planning long tasks, and integrations with GitHub, Slack, and issue trackers.
AI Snips
Chapters
Transcript
Episode notes
Match Reasoning Level To Your Workflow
- Use lower reasoning for fast iteration and higher reasoning when you want the model to take longer, deeper passes.
- Alexander recommends low reasoning for most flow and high when you’ll step away and want the model’s best answer.
Let The Agent Explore Your Repo Safely
- Let Codex inspect the repo by running safe terminal commands and reading files rather than hand-holding it.
- Approve sandboxed actions when prompted so Codex can execute and validate changes locally.
Compaction Extends Agent Memory
- Compaction enables Codex to run multi-hour agent loops by summarizing state into fresh contexts.
- This lets agents solve tasks longer than a single model context window without losing progress.