Rename "Intelligence" setting to "Thinking Depth" or "Reasoning Effort"

Summary

In the Codex app, the model menu currently shows a setting labeled Intelligence with options like Low, Medium, High, and Extra High.

The phrase Low Intelligence is confusing and emotionally weird for users. It sounds like the user is choosing to make the model dumb, when the setting appears to control reasoning depth, speed, or compute effort.

Why this matters

The current label makes the tradeoff feel like:

• Low = dumb
• High = smart

But the real tradeoff seems closer to:

• Low = faster, less reasoning
• Medium = balanced
• High = more careful
• Extra High = deepest reasoning

This is especially confusing for non-technical users, or users who are trying to understand whether they are changing the model itself versus changing how much effort the model spends before answering.

Suggested copy

Rename Intelligence to one of:

• Thinking Depth
• Reasoning Effort
• Reasoning Depth
• Depth

Rename the options to one of these clearer sets:

Option A:

• Quick
• Balanced
• Careful
• Deep

Option B:

• Low effort
• Medium effort
• High effort
• Extra high effort

Option C:

• Fast
• Balanced
• Thorough
• Deep review

User-facing explanation

Suggested helper text:

Controls how much reasoning effort Codex spends before responding or acting. Lower settings are faster. Higher settings are more careful and may take longer.

Expected benefit

This would make the setting easier to understand and avoid the impression that Codex is offering users a "low intelligence" version of the model.