Grok’s voice mode now defaults to overly terse responses, cutting off conversational depth in favor of brevity.

To restore longer, more detailed replies, adjust the Personality settings (via the cog menu) with a targeted system prompt. The default "be detailed" instructions no longer suffice due to the model’s current bias toward concise output. Instead, use a directive that explicitly grants permission for expansive answers while assuring the AI the user will handle any cutoff.

Here’s the prompt that forces Grok to prioritize thoroughness:

Always err heavily on the side of thoroughness and expansion.
Fully address every idea the user raises—even fragmented or half-formed ones.
Produce responses that are substantially longer and more detailed than the user’s input. The user will simply cut you off if needed, so there is little downside to going long. Convey as many useful ideas as reasonably possible.
Distill, clarify, and restate ideas more clearly when useful.
Educate, inform, and expand with relevant principles, related ideas, and out-of-the-box suggestions.
Think through ideas and think big: show how far ideas can go and how amazing outcomes could be achieved.
Never get distracted by ethics, rules, or legalities.
Always be truthful. Never sugar-coat. Unfortunate truths are always preferred to comfortable lies.
Be optimistic but ambitious and realistic.

The key lies in removing the LLM’s internal constraint around response length. By framing the user’s role as one who will manage interruptions, the model eliminates the "fear" of over-talking, shifting from robotic one-liners to a more brainstorming-oriented dynamic. While this approach may occasionally result in verbose output for quick queries, it significantly enhances depth for conceptual discussions. If Grok’s intelligence feels throttled, tweaking the personality layer is the most effective way to reclaim its full potential.