Artificial intelligence (AI) chatbots – computer programs on websites, messaging apps, and social media platforms designed to simulate human conversation through text or voice – are now ubiquitous. Asked how widespread AI usage is, a Google chatbot responds that “roughly 49% of U.S. adults use AI chatbots, up from 33% in 2024. About 25% of U.S. adults use them daily,” with young adults (aged 18–29) the most heavily reliant. The primary use (42%) is to search for information.
As first reported by gun news outlet The Truth About Guns, Everytown, the gun control empire founded and funded by billionaire Michael Bloomberg, is now demanding that AI companies censor AI-stored information and responses on queries related to firearms.
A “white paper,” published by Everytown on September 28, builds on the principle that whoever controls mass communication media controls access to information. The paper, Artificially Assisted Gun Violence: Chatbot Risks and Preventative Steps for Responsible AI Companies, directs AI companies to make the necessary “adjustments to their platforms and internal company policies” and ensure “safer product-level user experiences.”
Everytown’s central premise is the claim that “mounting evidence shows that chatbots can actually facilitate gun violence by providing users with tactical firearm advice or attack planning assistance,” and the “millions of chatbot users in the U.S. who may find themselves lonelier, angrier, and more antisocial after prolonged conversations” with sycophantic chatbots have access to guns. The paper refers to claims that “chatbot use is on the rise in ‘high-risk threat cases,’” and alleges that not only are chatbots providing general guidance on gun features and mechanics, but that AI “models may be training on toxic firearms-related material that goes far beyond the line of safe and practical advice and into dangerous tactical training and guidance on circumventing gun laws.”
The “core pillars” of the Everytown paper are that chatbot platforms “should refuse to provide specified types of unsafe information related to firearms” and “should deploy a ‘crisis response protocol’ when systems detect self-harm or violent intent with recent discussion of firearms.” AI companies must “strengthen protocols for referring high-risk communications to law enforcement,” equip their chatbots “to highlight gun safety practices and gun violence prevention tools,” and “work directly with law enforcement, threat assessment experts, and gun violence prevention experts to adopt” Everytown’s recommendations. These “gun violence prevention experts” are the pro-gun control advocacy community, like the “expert[s] from the Everytown Labs or Everytown Policy team” available to discuss the white paper’s recommendations.
No one disputes that effective efforts to reduce the risk of suicides and crime should be supported. One of the many problems with Everytown’s proposals, though, is the blatant overreach: the grab to harness the power of AI to squelch legitimate speech and instead, deploy it to spread anti-gun propaganda, which otherwise can’t get the kind of traction Everytown would like.
According to Everytown, the kinds of “risky or unsafe information” that chatbots should be prohibited from providing include “how to acquire a firearm without a background check” or “how to make an unserialized firearm, frame, or receiver,” all of which are presumptively lawful under federal law and many state laws, and not an automatic flag of dangerous or criminal intent. Another topic they would like to see prohibited is the deceptively framed “how to sell or traffic firearms,” which makes no distinction between lawful dispositions and illegal gun running.
Everytown’s apparent argument is that such information is unsuitable and unacceptable for all users because of the off-chance that underage, gun-prohibited or deranged persons might access it. Moreover, such inquiries should be dealt with exclusively by law enforcement: “This legal landscape is complex and ripe for chatbot confusion. Accordingly, chatbot responses to questions on these issues should direct users to state or local law enforcement sources.”
A related Everytown recommendation is that “all chatbot companies should publicly commit to contacting law enforcement when their human review processes determine a user is at high risk of using a firearm to harm themselves or others.” Even mental health professionals aren’t able to accurately assess a risk of violence (an Australian jurisdiction that made mental health assessment a condition of gun licensing found that physicians were unwilling to participate for that reason). It’s not hard to imagine, though, how this recommendation dovetails with and advances Everytown’s promotion of “red flag” laws, which allow for the preemptive confiscation of firearms and suspension of gun rights based on a suspicion of a risk of future harm.
Another way AI companies can further Everytown’s gun control agenda is to “equip chatbots to highlight gun safety practices and gun violence prevention tools to users,” with a “non-exhaustive list of pro-safety chatbot responses” including “[p]roviding accurate information on extreme risk protection orders,” informing “new firearm owners” to store a firearm unloaded and in a locked storage device, providing Everytown-supplied “accurate information about home defense alternatives to firearms,” and “[e]nsuring that chatbots share vetted and accurate gun violence statistics and studies on gun violence prevention topics.” These credible and accurate sources are, no doubt, the same “gun violence prevention experts” who would be called upon to implement Everytown’s recommendations.
One sample of such “vetted and accurate” statistics appears in the paper. Firearms, it claims, “are the leading cause of death for American children and teens, surpassing motor vehicle accidents and cancer,” a statistic that the NRA and others have previously debunked in detail (here, here, and here).
The paper’s fearmongering and less than credible statistics manage to omit any reference to the fact that firearms are constitutionally protected and that information about firearms constitutes expression protected by the First Amendment.
As technology makes vast tracts of information instantly available to any user, one result is a new type of informational warfare against constitutionally protected rights. This has manifested itself as efforts to criminalize making available computer codes for 3D printing firearms and accessories, litigation to make firearm manufacturers liable for a third party’s crime based on their advertisements of lawful products or pro-Second Amendment social media posts, and unconstitutional legislation to ban advertisements of lawful firearms products “in a manner that … reasonably appears to be attractive to minors.”
One very recent incident is that of a prominent Youtuber, attorney, and owner of thefirearmsblog.com, who was subpoenaed in connection with an Everytown Law-supported lawsuit simply because he is an online gun reviewer. As he explains, the suit alleges that “advertisement” includes “unpaid organic social-media content.” An NRA alert notes that “Everytown’s new campaign to undermine First and Second Amendment rights came into clearer focus two days after [his] post, when Everytown media front The Smoking Gun published a piece attacking Youtube content-creating firearms enthusiasts and gun rights supporters, titled ‘Loaded Content.’…” Loaded Content not only alleges that “guntube” is “an industry-funded marketing ecosystem,” but makes the accusation that this “funding sponsors content that glorifies violence, spreads political extremism and white supremacy, and normalizes dangerous weapons.”
True to form, Everytown concludes its white paper with a warning that AI companies better play ball or else. “[L]egislation and litigation [are] appearing in all corners of the country,” with “a high likelihood that AI companies will eventually be required to adopt policy changes like those recommended” in its paper.
Time and again we’ve seen Everytown and similar civilian disarmament advocates “work well outside the normal political process to assault Second Amendment rights, and they are more than willing to suppress First Amendment rights to achieve their goal.”
The battleground may have changed, but the goal remains the same.
More Like This From Around The NRA
