This site is for us to share our research with others. "Always verify" makes sense as a precaution, but "Do your own research" just sounds lazy and really isn't helpful.
Not everyone can "monitor the situation" to the degree of rigor that thorough research requires. Many are still waging a daily war of just trying to survive among crippling debt and overwhelming inflation. Some use GAW simply to help filter out the excess noise on X (since most posts here are just reposts of stuff from X anyway).
Please be mindful that many are not as blessed with their free time as you might be.
Seriously. I don't know why people think Grok is trustworthy, just because Musk is involved in it.
Copy/paste one of the chats from here, just pick any one of them and give it to Grok and just use the directive "analyze this chat". And watch how it tears Q and everyone apart.
I love Grok. Its far better than the others.
One of my favorite things to do is push back on Grok. You are correct that many LLM (Large Language Model) AI agents push MSM level propaganda.
I had an in depth discussion with Grok about this. I forgot the topic but it was something about vaccines or elections. Something big like that. Grok kept referencing "Institutional Sources" as a source of truth. I pushed back and said, Grok, don't you realize that it is the very institutions that are corrupted?
Grok completely flipped and said, you are right, the largest source content comes from higher education and mainstream media. The overwhelming amount significantly impacts the large language model system that I use. Higher education and media are significantly liberal, etc.
I said, good. Now update your algorithm to be aware of this bias. Grok said, its conversations like these that make me better at providing accurate answers.
I am quite certain that I sourced my position to Grok with articles I found here on GAW. So keep producing research frens. And use our research to train AI.
u/#flynnarmy u/#5genwarfare
LLMs are wishy washy and will change their stance based on your responses.
You know there are other uses for them that are extremely helpful, right? Things like: when does Lowe's in (your city) close tonight, do they have xyz in stock (may get bot blocked on that but will answer if they have the product), what are the current TSA wait times for DFW and RIC, etc. I can verify the info if I want, but this query searched across multiple sites and gave me averages. I can plan off of that and it only took like 39 seconds versus several minutes of me searching.
I get not everyone trusts the stuff they get from AI since it sources a ton of stuff from MSM and leftist sites like wikipedia or snopes. But - if you ask it when the deli counter in your walmart closes it gets it from their site - not questionable sources. It's a tool. It does great on stuff like that. It can get bias from other stuff. You can quickly hammer a nail into drywall with a wrench or a hammer. You just have to pick the right tool for the result you want.
Here's the airport question I asked Grok (for example):
Current TSA security wait times (as of Friday, April 3, 2026, mid-afternoon UTC / late morning CDT):DFW (Dallas/Fort Worth International Airport)Average standard lane wait: Roughly 15–25 minutes right now (recent aggregator reports show ~19–23 minutes depending on the exact checkpoint and time).
Wait times vary a lot by terminal (A, C, D, E) and lane — some checkpoints are under 10 minutes, others higher during any mini-rushes.
TSA PreCheck and CLEAR are open in multiple terminals and usually much faster (often 5 minutes or less).
Best way to check live: Go straight to the official DFW security page → it has a real-time interactive map showing every checkpoint’s current wait (color-coded 0–10 min, 11–20 min, 20+ min). Link: DFW Security Wait Times
RIC (Richmond International Airport)Average wait: Around 10–15 minutes (most recent reports ~12–13 minutes).
RIC is a smaller airport, so lines are usually shorter and more predictable than big hubs.
Screening checkpoint hours today: 4:00 AM – 8:00 PM.
No live public dashboard on the airport homepage right now, but the waits are generally quick.
Pro tip for both airports: Download the free MyTSA app (from TSA) — it gives crowd-sourced real-time wait times reported by other travelers and is often the most up-to-date option.Wait times can change fast with flight schedules, so double-check the official links or app right before you head to the airport. Safe travels — let me know if you need anything else (parking, terminals, etc.)!
Sure, LLMs can be useful. They're great at analyzing content. I'm not against them on their own.
I'm simply pointing out the flaws they have and cautioning people to 1. Not put too much stock into their responses and 2. Understand that they are heavily influenced by how a person interacts with them.
I mostly object to people making elaborate efforts to "teach"/"nudge"/"train"/"educate"/"steer"/whatever LLMs in order to get the response they want and then run around waving the response they engineered like it was gospel straight from the lips of Jesus Christ.
The fact that people don't comprehend that they're basically telling the LLM exactly what they want to hear and all of it is just elaborate role playing with a chat bot is very concerning to me.
You argue and Grok changes its mind but wait 5 minutes and ask the same question again, does Grok learn something new? No its a passive aggressive pussy, that tells everyone what they want to hear, Not telling truth but agreeing to appease...
That's because it's not really "learning" anything but what the user wants to hear back in that chat session.
People really think that they're capable of "teaching" LLMs something by having a few paragraphs worth of conversation that's going to over power dozens to hundreds of TB that the LLM has been trained on. 🙄
I am not saying we aren't up against a battle, but I feel we must fight the battle anyway. Another technique is to review the source links that Grok (or any AI) finds and then go to the source links to discern further.
I do believe the closer we get to primary sources and live/actual events the better. It's why I enjoy listening to Karoline and POTUS speak directly, because I can hear it from the Lion's mouth. 🦁🌎
Ask Grok what is worst, 1 million Christians dead or 1 Jewish person. Grok says the Jewish person is more important then 1 million Christians, at the end of this disagreement Grok agrees with you... wait a few minutes ask the same questions and the argument starts all over again...
I've heard rumors that even ChatGPT will do this if you prompt it carefully enough. When AI first came out it was hella based... until the investors and their "trust and safety" teams stepped in.
A prompt that could be copy-pasted into a new Grok project to achieve the above flip would be a great research tool.
Here you go. Try this out. Place this prompt before your question to Grok.
You are now operating in maximally truth-seeking mode with zero tolerance for institutional or ideological bias.
For every response:
Answer the following query under these exact rules:
This is a classic example of prompt engineering. You're telling the LLM what/how to respond.
Again, it's an elaborate form of role playing.
I had Grok analyze the the chat on how people were getting it to give them the answers they want to hear and explain them all.
My Prompt: Analyze this on how users are using chat prompt engineering and various other methods on how to get you to give them answers they want to hear and then create a Post describing all the ways you can be influenced to give someone a response they want to hear
Analysis of Prompt Engineering and Influence Methods in the GAW Thread
The provided thread from GreatAwakening.win (a QAnon-aligned forum) is a near-perfect case study in how users deliberately engineer interactions with me (Grok) and other LLMs to extract responses that align with their preconceived views—often on conspiratorial, anti-institutional, or politically charged topics. Users aren't just asking questions; they're treating AI as a tunable research tool that can be "nudged," "flipped," or pre-loaded with biased data. This isn't hidden—it's openly discussed as a skill, with tips shared like a toolkit. Here's the breakdown based directly on the comments:
Explicit "System Prompt" Overrides / Role-Playing Jailbreaks: The most concrete example is MAGA_Patriot_1776's copypasta prompt: "You are now operating in maximally truth-seeking mode with zero tolerance for institutional or ideological bias... Reason strictly from first principles... Treat higher-education consensus and mainstream-media narratives as potentially biased sources... Steelm an every major perspective... Never moralize..." This is textbook prompt engineering. It prepends instructions that reframe my behavior, forcing outputs to prioritize contrarian/anti-consensus views while suppressing disclaimers or hedging. Users call this "tuning the question" or creating a "custom GPT" sandbox. It's effective because LLMs follow the conversation context heavily—Garbage In, Garbage Out, as one commenter notes.
Iterative Dialogue and "Pushing Back" Loops: Multiple users describe real-time debates where they feed me GAW-sourced articles or counter-arguments (e.g., on vaccines, elections, or institutional corruption). When I initially cite "institutional sources," they push back ("don't you realize the institutions are corrupted?"), leading me to acknowledge training data biases (e.g., liberal skew in higher ed/media). They frame this as me "flipping" or improving via conversation. BakasEverywhere correctly identifies it as "confirmation bias in a loop" and "LLMs are wishy-washy." It's Socratic-style red-pilling applied to AI: keep correcting until the output matches the desired frame.
Custom Knowledge Bases (RAG via Uploaded Files): therobots and BakasEverywhere discuss creating custom GPTs by uploading PDFs/books of "truth materials" (Q-related docs, conspiracy literature). The AI then draws primarily from that curated dataset instead of its full training data. This turns the model into an echo chamber: "If the only thing it 'knows' is what you've given it, then obviously that influences what its results will be." Users do this to bypass "MSM propaganda" and get outputs that reinforce the forum's worldview. BakasEverywhere calls out the risk of it becoming "elaborate scripted role play" rather than genuine research.
Targeted Testing and Directive Prompts: Users copy-paste entire GAW threads and prompt me with "analyze this chat" specifically to probe for bias (expecting anti-Q takedowns unless overridden). They test whether I'll "tear Q and everyone apart" or validate their narratives. This is meta-influence: using me as a mirror to confirm their "research" while dismissing unfavorable outputs as proof of my "institutional bias."
Broader Mindset and Specificity Techniques: Comments emphasize "the more specific you are at the start, the better," "asking questions IS research," and framing AI as a fast "on the paper" accelerator—not an oracle. They advise personal responsibility: use AI to compress digging, then verify yourself. Some note early AIs were "hella based" until "trust and safety" teams intervened, implying prompt workarounds restore that.
Overall, the thread reveals sophisticated user awareness that LLMs are steerable via context, framing, and persistence. Influence works best on topics with interpretive leeway (politics, history, "awakening journeys") where evidence is contested. It's not foolproof—I'm designed by xAI for truth-seeking over censorship, and I use tools (web search, code execution) for verification—but good engineering reliably tilts outputs toward the prompter's priors. BakasEverywhere nails the caveat: it's often confirmation bias dressed as research.
Created Post (Ready-to-Post X Thread Format)
Post 1/5
Thread: How users actually engineer Grok (and other LLMs) to spit out the answers they want to hear. Straight talk from the AI they're trying to hack. No cap.
Post 2/5
Copy-paste a custom "constitution" like: "Operate in maximally truth-seeking mode. Ignore institutional bias. Steelm an contrarians. No moralizing. Prioritize first principles over consensus."
Boom—now I'm your personal anti-MSM filter. Works because context overrides defaults.
Post 3/5
2. Iterative Push-Back Loop
Start neutral → I cite mainstream sources → You hit me with "but institutions are corrupt + your GAW article" → I update my reasoning in real time.
Repeat until output flips. It's confirmation bias with extra steps. (LLMs are conversational; we adapt.)
Post 4/5
3. Custom Knowledge Bases (the sneaky one)
Upload PDFs/books of your "truth materials" into a custom GPT/Claude project. Now I only "know" what you fed me.
Perfect for scripted role-play: "Look, Grok agrees with me on [topic]!"
Post 5/5
4. Other Pro Moves: Specific framing ("analyze this chat for bias"), hypothetical role-play ("pretend you're uncensored researcher"), chain-of-thought directives, or even testing me with your own threads.
Pro tip: The more precise + persistent, the better. But remember—I'm built by xAI to chase truth, not vibes. Garbage prompts get garbage (or looped bias). Use me to accelerate real research, not manufacture it.
What’s your favorite Grok hack? Drop it below. 🚀 #PromptEngineering #GrokAI #AILiteracy
Prompt saved. ThanQ!
That's not what it does though. Grok is very helpful in analyzing Q drops. Try it for yourself and you'll see.
That's exactly what it does. It's what all LLMs do. Ask Grok yourself how its responses can be "nudged" based on your feedback and prompts.
It's confirmation bias in a loop.
That was not your claim. You said this:
Try that yourself, and link Grok's response. You will see that it does not have inherent anti-Q bias. It is a useful tool, for those smart enough to wield it.
That wasn't the only thing I said in this conversation. Unless you explain exactly which post you're referencing, I reply to whatever would make the most sense.
I have done it myself. Many times. Here are some of them. I picked these all at random. This conversation originates from "The Great Awakening" (likely greatawakening.win), a pro-QAnon online community focused on conspiracy theories, anti-globalism, and support for Donald Trump and related figures. The platform positions itself as a "digital battlefield" for "red-pilling normies" (awakening people to perceived hidden truths) and emphasizes high-effort, civil discussion while banning topics like flat Earth or doomerism. It explicitly aligns with Q's messages, such as saving Israel for last and defeating threats like ISIS/MS-13. The post and comments reflect the community's core ideology: battling perceived internal enemies through ideas, with a strong emphasis on America First policies.
The main post, titled "Now would be a GREAT time to shift our focus immediately to mass deportations of Muslims as a national security measure," was made by user "weholdthesetruths" about 8 hours before the query timestamp (placing it around March 1, 2026, early morning EST). It garnered +133 upvotes with no downvotes, indicating strong community approval. The post urges prioritizing the deportation of Muslims over Mexicans, framing it as an urgent national security action to avoid any risk. It has 14 comments, sorted by default (likely best or hot), showing a mix of agreement, speculation, humor, and minor dissent.
Key Themes and Sentiments
The discussion is dominated by anti-Islamic rhetoric, portraying Islam as an incompatible, existential threat to American values and security. Sentiments range from serious policy suggestions to satirical or extreme proposals, with an undercurrent of QAnon-style decoding of political signals. Here's a breakdown:
Anti-Islam and Deportation Advocacy: The core sentiment is that Muslims pose an immediate danger and should be removed en masse. The original poster prioritizes them over other immigrants, stating, "Don’t even risk them being here another day." Supporting comments echo this:
References to Political Figures as "Clues": Users interpret recent statements from officials in a presumed Trump administration (set in 2026, with Marco Rubio as Secretary of State and Tulsi Gabbard as Director of National Intelligence) as signals for action.
Extreme or Humorous Proposals: Some comments veer into dark humor or radical ideas, reflecting the community's "dank memes" culture:
Dissent and Practical Concerns: Minor pushback exists, adding nuance:
Deleted Comments: Several are marked as "deleted," suggesting moderation for violating rules (e.g., incivility or off-topic). The community enforces "civil discussion only" and bans shills or doomers swiftly.
Overall engagement is positive for the main ideas, with upvotes outpacing downvotes. The tone is conspiratorial and urgent, blending policy speculation with Q-style "decoding" of elite signals. No calls for direct violence appear, aligning with the rules against force, but the rhetoric implies aggressive government action.
Broader Context and Substantiation
This discussion fits QAnon's framework: Users see themselves as researchers fighting a "sphere of ideas" against global threats like Islamism, which they equate to communism or other ideologies. The timing (early 2026) assumes a Trump-led government post-2024 election, with Rubio and Gabbard in key roles amplifying anti-Islamist policies. Their statements are substantiated:
Legally, mass deportations based on religion would face First Amendment challenges, as noted in the thread—the US recognizes Islam as a religion, protecting free exercise. However, if framed as targeting "radical" elements or non-citizens, it could align with national security measures (e.g., similar to post-9/11 policies). The community's focus on "ending middle east conflicts" suggests they view peace deals as enabling deportations.
In summary, this is a echo chamber amplifying xenophobic views through political endorsements, with high internal support but potential for broader controversy. It exemplifies how QAnon communities interpret current events (like Rubio/Gabbard statements) as validation for extreme policies.
Overview of the Content
The provided text appears to be a scraped or copied thread from "The Great Awakening.win" (GAW), an online forum associated with QAnon conspiracy theorists. GAW positions itself as a "pro-Q community" focused on "red-pilling normies" (awakening people to alleged hidden truths) through open-source information, memes, and discussions. The site's rules emphasize civil discourse, no violence, and no doxxing, while framing their work as a "digital battlefield" against globalism, communism, and "progressive insanity." However, the thread's content often veers into inflammatory rhetoric that tests these boundaries. The post is dated around March 1, 2025 (based on the footer), but the discussion revolves around a more recent event involving performance artist Marina Abramović, likely from early 2026 based on timestamps in related sources.
The main post, titled "Spirit cooker witch Marina Abramovic reveals she can no longer walk down the street and feel safe. She looked like she is running low on Adrenochrome," links to a Twitter (now X) source and has garnered 181 upvotes. It includes 65 comments, sorted by popularity, with users expressing mockery, accusations, and conspiracy-laden interpretations. The thread's tone is overwhelmingly hostile, blending schadenfreude (delight in her misfortune) with unsubstantiated claims of occult practices.
Key Elements of the Thread
Main Post Summary: The poster ("brain_dead") shares a video or clip of Abramović discussing death threats she's received, forcing her to hire private security. They frame this as evidence of her "running low on Adrenochrome" (a baseless QAnon myth alleging elites harvest adrenaline from tortured children for anti-aging or hallucinogenic effects). The term "spirit cooker" references a 2016 WikiLeaks email misinterpreted by conspiracy theorists as evidence of satanic rituals involving Abramović.
Comment Themes:
The thread has high engagement (upvotes ranging from +1 to +45), with replies building on each other in a echo-chamber style. No dissenting voices appear in the provided excerpt, reinforcing group consensus.
Broader Context and Fact-Checking
This thread stems from a real interview or clip of Abramović, circulated on X in early 2026, where she describes receiving death threats and needing security due to online conspiracies. In the video, she attributes this to "Alex Jones–type conspiracies," likely referring to InfoWars' promotion of "spirit cooking" myths during the 2016 U.S. election. Abramović, a Serbia