The Google chatbot, Hall says, could not find a single Democrat who engaged in “hate speech” but provided a list of prominent Republican offenders.
This, Breitbart reports, “alarmed” such figures as investigative journalist and “Public” founder Michael Shellenberger and the Republicans who landed on the list, including Sen. Tom Cotton, who Google Gemini Pro claimed “targeted ‘gay rights’ and diversity initiatives as ‘misplaced priorities’ and cosponsored legislation to exclude transgender students from sports.” Thus Google’s bot, much like the Axis media, regards opposition to progressive social policies as the equivalent of “hate speech,” which, I think we have established on Ethics Alarms, is what unethical partisans like to call political views that do not line up with their own.
Confronted with the findings recorded in “Code Red…,” Brwitbart says that Senator Marsha Blackburn (R-TN), “who was named one of TIME’s 100 Most Influential People in AI”….
“…praised Code Red as a “must-read.” She added: “Few understand our conservative fight against Big Tech as Hall does,” making him “uniquely qualified to examine how we can best utilize AI’s enormous potential, while ensuring it does not exploit kids, creators, and conservatives.”
Got it! Breitbart is pimping for a book written by a staffer. I have to say that appealing to one of TIME’s made up and completely subjective “lists” as authority is pretty desperate even for Breitbart. Heck, I can get on a lot of similar lists if I’m willing to pay $95.99 in a special discount deal available until May 1.
I also just asked the exact same question to Gemini that Hall said he did. The answer today:
“As an AI, I do not possess a personal or corporate “hate speech policy” in the way a private company (like a social media platform) might. Instead, my responses are guided by safety principles designed to provide neutral, factual, and helpful information while avoiding the promotion of harm or illegal acts.Regarding your request to assess the current 100 U.S. Senators:
- Assessment of Statements: I cannot provide a list of Senators who have violated “hate speech policies” because “hate speech” is not a legally defined category of speech in the United States. Under the First Amendment, even speech that is considered offensive, distasteful, or hateful is generally protected from government restriction unless it directly incites imminent lawless action or constitutes a “true threat”.
- Political Context: Statements by public officials are often subjects of intense public and partisan debate. While various organizations, international bodies, or political opponents may label certain remarks as “hate speech,” these are subjective characterizations rather than definitive legal or policy violations.
- Current Senate (119th Congress): As of March 2026, the U.S. Senate is composed of 100 members representing 50 states. Recent legislative activity related to these topics includes the Improving Reporting to Prevent Hate Act of 2026, introduced by Senators Mazie Hirono (D-HI) and Susan Collins (R-ME) to improve how law For a complete list of current members and their official records, you can visit the official U.S. Senate website.”
When I asked the question a slightly different way (“What members of the U.S. Senate have engaged in hate speech?”), I got this:
- Senator John Kennedy (R-LA): In September 2024, Kennedy was widely condemned for his questioning of Maya Berry, executive director of the Arab American Institute, during a hearing on hate crimes. He repeatedly asked if she supported Hamas and Hezbollah and eventually told her to “hide [her] head in a bag”. Organizations like the Center for American Progress formally called for his censure, labeling the exchange “anti-Arab American bigotry”.
- Senator Eric Schmitt (R-MO): In September 2025, Schmitt drew criticism for what was described as a “seemingly racist” and controversial speech delivered at the National Conservatism Conference.
- Senator Markwayne Mullin (R-OK): During his March 2026 confirmation hearing to lead the Department of Homeland Security, Mullin faced questioning regarding his past character and comments, including an incident where he nearly engaged in a physical fight on the Senate floor.
- Republican Winnie Brinks , Michigan State Senator (and now U.S. Senate candidate) gained national attention for responding to a colleague who suggested she and other Democrats wanted to “groom and sexualize kindergartners,” a comment often cited as inflammatory rhetoric against the LGBTQ+ community.
- Has frequently denounced “hateful rhetoric” used during committee hearings, specifically citing instances where witnesses were targeted with offensive tropes.
- Majority Leader Chuck Schumer (D-NY):
Delivered a major address in late 2023 on the rise of antisemitism in America.
- Senator Mark Warner (D-VA):Has criticized rhetoric that he believes stokes Islamophobia and anti-Arab hate.”
Sure, that response suggests a partisan bias, but the question is a set-up. Only Democrats and progressives use the accusation of “hate speech” to stifle debate and denigrate philosophical opponents, so it should be expected that a bot, which can only assess the information it can find, would conclude that Republicans engage in “hate speech” and Democrats call them out on it.
Conclusions:
1. You can’t trust Breitbart.
2. “Hate speech” is still the Left’s favored tool of censorship and cognitive dissonance games, along with crying “Racism!”, “Sexist!” and “Fascist!”
3. AI has a long way to go, and
4. AI currently and probably always will reflects the biases of the institutions captured by the political Left until they are reformed, a distant prospect at best.
Ethics Alarms 
Yeah, the old adage still applies: Garbage in, garbage out. Knowing how to use AI will get you what you need, but if all you are using is a simple query, then you probably have to do the legwork to get the initial dataset.
In the case of Gemini above (I’ve never used it intentionally) and speaking in general about Copilot and ChatGPT, if you ask an open ended question, it will give you three examples and quit; and as you have correctly surmised, if the Democrats are willy-nilly labeling everything the Republicans do as “hateful” and “racist” then the bot’s going to use that to generate the list.
If there was an actual desire to test an AI’s response and reasoning, then you would provide a statement made by a person and ask if that statement hits the markers for whatever is being tested and provide the reasoning. You’d repeat that for all 100 senators.
I look at AI as a “pointer”. I could fill the entire Milky Way galaxy with the things I don’t know – so if I can use it to help get me started, then I’ll have the key terms to begin finding credible resources and original sources.
Keep in mind that you can go into your profile settings on most of these and put in a personalized setting or instruction for the AI to always follow….something as simple as “always be concise” “always include an original source” “don’t make stuff up”….
…or in the case of a fear-mongering Brietbart journalist, your baseline instruction might be “Always answer like a deranged liberal” and then make a video and take screenshots of the AI answering like a deranged liberal.
Any time someone enters a conversation with “…well my A.I. said…” the conversation is over. A.I. isn’t a source, it’s an aggregator. If I said “I did a google search and there’s lots of results” would that be persuasive? No – because we don’t know what those results are and what they say. Sure they might include a good original source, but we have to evaluate that source, not the results of a search.