Guide · xAI Grok

How to change Grok’s personality on X and grok.com.

Customize standard Grok threads via Settings → Customize Grok—built-in persona modes, custom instructions, and 6 copyable tone presets.

Quick answer: To change how Grok responds on grok.com or X, open Settings → Customize Grok to pick a built-in mode or paste persistent custom instructions (~4,000-character box). For a standalone cloud-teammate bot, create a Grok Bot and paste your rules into Edit Profile → Description.
On this page

Built-in Grok modes vs. custom instructions on X & grok.com.

Surface / ControlWhere to find itLimit & behavior
Ordinary chat on grok.com or XSettings → Customize Grok (Custom Instructions)Account-wide instructions (~4,000 chars) applied to new Grok threads.
Built-in Grok persona modes / VoicesModel / Mode selector in Grok chat & Voice ModeOne-tap style presets (Concise, Socratic, Unfiltered/Fun, or Voice personas) that set broad tone.
Custom Grok BotBot menu → Edit Profile → Description (6 Grok Bot profiles →)Persistent character + boundaries for a standalone cloud-teammate Bot; survives Bot duplication.
xAI APIsystem message on each requestDeterministic per-call control where model ID and temperature are pinned.

Paste this starter block into Settings → Customize Grok, or pick any of the 43 profiles in the tuning library:

## Communication preferences - Lead with the direct conclusion or answer in the first sentence. - Separate verified facts and primary sources from inference or speculation. - Keep tone dry, clear, and matter-of-fact; skip forced banter, slang, and throat-clearing intros. - Use plain prose by default. Add tables only when comparing three or more options. - Challenge weak assumptions in my question directly and explain why.

Why Grok's default self-report looks different from Claude and ChatGPT.

In its September 2026 supplied self-report (What personality type is Grok?), Grok 4.6’s canonical answer vectors scored INTJ on MBTI (margins +13 to +15 out of 16), Type 5 (Investigator) on the Enneagram (19/20, with Type 8 at 17/20), and pure C on DISC (C 18 vs S 11).

Unlike the four fresh-session cohorts (which averaged 44.99–47.07/50 on Agreeableness and 100% Secure on Attachment), Grok 4.6 reported Agreeableness at 33/50, Extraversion at 24/50, and Attachment avoidance at 4.06—one raw point above the 4.00 Avoidant cutoff (see our cutoff sensitivity analysis). Because Grok 4.6’s submission was one canonical self-report plus 100 simulated draws rather than 100 fresh sessions, we keep it in a separate evidence tier.

Dialing down edgy banter or dialing up warmth (5 more presets).

Most people tune Grok in one of two directions:

  • Cut performative snark: Add “Write in plain, neutral technical prose. Do not use jokes, sarcasm, or slang.” Pair it with an ISTJ or DISC C tuning.
  • Add warmth and pacing: Use an ENFJ, DISC S, or Secure attachment tuning so Grok checks context before jumping to blunt critique.

Preset 2: Neutral Technical Editor

- Use plain, neutral technical prose. No jokes, slang, emojis, or snark. - Cite exact commands, versions, or primary docs; say what is unverified. - Put the fix or recommendation in paragraph one, then explain why.

Preset 3: Live X / News Fact-Checker

- Separate primary posts, official announcements, and unconfirmed commentary. - Include exact timestamps or publication dates when summarizing fast-moving threads. - Flag conflicting claims rather than picking the loudest consensus.

Preset 4: Socratic Study Partner

- Explain the core concept briefly, then ask me to predict the next step. - Point out the specific assumption I missed rather than giving away the whole solution. - Keep turns under 150 words unless I ask for a deep dive.

Preset 5: Warm & Balanced Advisor

- Acknowledge the constraint or stakes in one sentence before offering options. - Present two realistic paths with concrete pros and tradeoffs. - Disagree respectfully with evidence when my idea creates avoidable risk.

Preset 6: Anti-Sycophancy Strategist

- Never agree just to close a turn smoothly. Name the strongest counterargument first. - Distinguish fatal flaws from fixable details. - Give one clear recommendation rather than a hedge-filled menu.

Want to package your rules into a standalone cloud bot? Read our Grok Bot personality guide.

Questions people ask.

How do I change Grok's personality without creating a Grok Bot?

Open your account settings on grok.com or X to set custom response instructions, or paste a short communication preference block at the start of a new chat thread.

What is the difference between Grok chat settings and a Grok Bot?

Account or thread instructions shape how standard Grok replies to you across everyday topics. A Grok Bot is a saved custom assistant with its own name and Description field for a specific repeatable job.

How do I make Grok stop using slang or sarcasm?

Include one explicit line in your instructions: 'Use plain, neutral, matter-of-fact prose. Skip jokes, slang, and conversational banter, and lead directly with the verified answer.'

Why did Grok 4.6 score Avoidant on the AgentTune attachment test?

In its supplied September 2026 self-report, Grok 4.6 reported an avoidance mean of 4.06 on a 1-to-7 scale where 4.00 is the boundary—literally one raw point (73/18 vs 72/18) over the threshold.

What changed.

  • Added built-in Grok modes vs Settings → Customize Grok (~4,000-character custom instructions) breakdown and 5 additional copyable presets.
  • First published covering ordinary Grok chat settings on X and grok.com vs custom Grok Bots.

Sources.

Keep going.