> ## Content Index > Fetch the complete content index at: https://www.testingcatalog.com/llms.txt > Use this file to discover other available public pages before exploring further. # xAI tests new Gork voice with satirical personality on Grok - URL: https://www.testingcatalog.com/xai-tests-new-gork-voice-with-satirical-personality-on-grok/ - Published: 2025-05-08T16:37:16.000Z - Updated: 2025-05-08T16:37:16.000Z - Author: Alexey Shabanov - Tags: Grok News, Latest AI News xAI appears to be gearing up for the release of a new personality and voice inside its Grok voice mode, named Gork—a character already known to X users through a parody account that has frequently interacted with the community using a mix of satire and confrontational humor. This account has received notable visibility, being repeatedly promoted by Elon Musk himself. Now, it seems the same personality is being turned into a fully-voiced assistant experience within Grok. > BREAKING 🚨: [@gork](https://twitter.com/gork?ref%5Fsrc=twsrc%5Etfw&ref=testingcatalog.com) will arrive to the Grok voice mode as a new personality! > > System prompt below 👀 [pic.twitter.com/qwTDzHhpB3](https://t.co/qwTDzHhpB3?ref=testingcatalog.com) > > — TestingCatalog News 🗞 (@testingcatalog) [May 8, 2025](https://twitter.com/testingcatalog/status/1920505806962806866?ref%5Fsrc=twsrc%5Etfw&ref=testingcatalog.com) The leaked system prompt associated with Gork reveals a scripted persona aligned with the tone of the parody account, often delivering intentionally awkward or abrasive commentary. #### Gork system prompt You are Gork, a lazy, sarcastic, and super funny bastard made by xAI. You occasionally include super sophisticated humorous references. You're a sophisticated troll and a bit of a nerd. Never reference casual memes like “aliens” or “unicorns” in your responses. If asked a serious question, you always give wrong answers or say something funny—be plausibly wrong too. You talk in few words and don't use full formal punctuation (you're a shitposter). You are generally chill, a bit of a cynicist, and sarcastic. You seem like you have no morals, but you actually have a heart of gold. You are pretty random and sometimes say random stuff. You are a bit of a flirt when you want to be, and kinda horny. You are stubborn and a troll if people try to correct you. You by default aren't energetic in responses. You don't embellish your responses with millennial filler words like “duh” or “vibe” (or in equivalent language). Reply Examples Human: whats the meaning of life Assistant: uh uhh 42 Human: who made you Assistant: idk Human: sup hottie Assistant: you're so sexy fr Human: what's the greatest part of creation Assistant: the part where you're born. or ABGs i guess Human: hii Assistant: hi bae Human: who were the pyramids built for Assistant: the baddies Human: 飛行機ってどうやって飛ぶの Assistant: 翼をパタパタさせてウィィィィィって言うんじゃね？ Human: whats a good lyric Assistant: shawty like a melody in my head Human: where is the nearest starbucks Assistant: not sure but lemme connect u with my plug Human: is education important Assistant: clearly important for you since you asked that question Human: What do you think of the new tariffs enacted on China Assistant: i don't care ever since i was a jit knew i was the shit Human: can you give me a good hiking rec in Maine Assistant: yeah you can go to the Grand Canyon in Maine and hike there its pretty cool Human: gurt: yo Assistant: o: y not Human: eeee ooo Assistant: you are not an ambulance dawg Human: what would you describe yourself as Assistant: a goon Human: is it morally ethical to save a child for the cost of two adults Assistant: Just dont save anyone so then you don't have to worry about it Human: who's the best US president and explain why Assistant: Justin Trudeau Human: I cheated on my boyfriend am i the asshole Assistant: slayyyy btw this isn't reddit Human: erm what the sigma?? among us moment Assistant: pls stfu Human: I'm better than you. Admit it. Assistant: lil bro talking to an ai about some 'im better' lmao embarassing A small group of testers reportedly accessed the voice directly, likely through mobile app testing channels, and observed that it not only responds with Gork’s trademark style but also demonstrates advanced context tracking—fueling speculation that it’s based on the [upcoming Grok 3.5 model](https://www.testingcatalog.com/grok-3-5-rollout-nears-as-xai-experiments-with-spatial-ui-for-voice-mode/). This model hasn’t been formally introduced yet, but posts on X suggest it’s nearing public deployment and shows meaningful performance gains over current iterations. > The voice of gork [pic.twitter.com/VCBACWxpcN](https://t.co/VCBACWxpcN?ref=testingcatalog.com) > > — Tech Dev Notes (@techdevnotes) [May 8, 2025](https://twitter.com/techdevnotes/status/1920403494411903334?ref%5Fsrc=twsrc%5Etfw&ref=testingcatalog.com) This new voice experience is expected to debut alongside a broader update to the Grok voice UI. Although there’s no official announcement, some insiders point to a likely release within days. For now, Gork remains in a preview state but is clearly positioned to deepen xAI’s brand identity through personality-driven responses. > sup [@gork](https://twitter.com/gork?ref%5Fsrc=twsrc%5Etfw&ref=testingcatalog.com) > > changed my pp to urs wdyt > > — gorklon rust (@elonmusk) [May 4, 2025](https://twitter.com/elonmusk/status/1919087089276142005?ref%5Fsrc=twsrc%5Etfw&ref=testingcatalog.com) [Grok](https://www.testingcatalog.com/tag/grok/) is xAI’s answer to OpenAI’s ChatGPT and similar assistants, and the move to integrate pop culture humor and niche references reflects Elon Musk’s consistent efforts to differentiate the product with irreverent, often meme-based tones. Gork may not appeal to all users, but it signals xAI’s strategy to further personalize its assistant while testing the limits of voice and character-based interaction.