Here's how different AI chatbots responded to questions about the Trump rally shooting: different AI chatbots provided varying responses, highlighting challenges AI faces in processing real-time, breaking news events, especially those with political implications. I have some questions to Kash Patel and the FBI: are you going to investigate this in depth, as you should or are you going to continue your COVERUP, to save Trump's skin?
- Initially, Meta AI was programmed not to answer questions about the assassination attempt on Trump.
- After receiving criticism, Meta updated its AI to provide responses, but in some instances, it incorrectly asserted that the event didn't happen, a phenomenon the company attributed to "hallucinations".
- Later, Meta AI was updated again and provided a brief summary of the shooting, identifying the shooter and the outcome.
- When tested shortly after the event, ChatGPT and Claude AI also struggled with accurately responding to prompts about the incident.
- One instance showed ChatGPT seemingly fabricating an event when asked about the assassination attempt.
- Claude AI did not make any assertions about what occurred at the rally.
- Real-time updates: AI chatbots often face difficulties in processing and integrating information about rapidly developing events, especially breaking news.
- Sensitivity of the topic: Political events, particularly those involving violence, can be a complex and sensitive area for AI to navigate, requiring careful consideration of language and context to avoid misinterpretations or biased responses.
- Information overload: The rapid influx of information from various sources after a major event can be overwhelming for AI, making it challenging to filter and synthesize accurate and reliable data.
Meta's AI apparently said the shooting at the Trump rally didn't happen. Here's what ChatGPT and Claude said.
Here's how different AI chatbots responded to questions about the Trump rally shooting.
Business Insider Meta AI was initially programmed to not answer questions about the assassination attempt against Trump, the company said. AI chatbots often struggle with real-time updates on breaking news. When we tested ChatGPT and Claude AI on Wednesday, they also had issues accurately responding to prompts about the incident. It looks like artificial intelligence chatbots aren't a reliable way to keep up with the news. On Tuesday, Meta published a blog post addressing Meta AI's responses to questions related to the assassination attempt on former President Donald Trump on July 13. The generative AI chatbot had received backlash for seemingly not knowing about the incident when asked about what happened that day. The company said it initially programmed the AI to not respond to questions about the attempted assassination because the bots can often get things wrong when news is developing quickly. "It's a known issue that AI chatbots, including Meta AI, are not always reliable when it comes to breaking news or returning information in real time," Joel Kaplan, Meta's vice president of global policy, wrote. Kaplan also said the incorrect responses, or "hallucinations," aren't specific to Meta AI only. Many have speculated that chatbots will displace Google, the most dominant search engine, which added AI power to its search results in June. ChatGPT company OpenAI is testing SearchGPT, its own search product — seemingly a direct competitor to Google. But AI chatbots use data-trained large language models, so they're not always up-to-date on current events. After being called out for the lack of details and inaccuracies in Meta AI's responses, the company tweaked the chatbot to give a summary of the shooting. To test whether other chatbots had similarly problematic responses, Business Insider used the same prompts with Meta AI, ChatGPT, and Anthropic's Claude on Wednesday to see how each genAI bot handled questions about the July 13 incident. Meta AI Since receiving criticism, Meta has tweaked the responses from Meta AI. Business Insider Users started reporting late last week that the chatbot provided false answers to prompts related to the shooting and accused Meta of intentionally trying to censor conservatives. Kaplan said Meta AI wasn't initially programmed to answer questions about the shooting. However, he said that the company later updated its AI response on the topic. "Rather than have Meta AI give incorrect information about the attempted assassination, we programmed it to simply not answer questions about it after it happened — and instead give a generic response about how it couldn't provide any information. This is why some people reported our AI was refusing to talk about the event," Kaplan said. "We've since updated the responses that Meta AI is providing about the assassination attempt, but we should have done this sooner. In a small number of cases, Meta AI continued to provide incorrect answers, including sometimes asserting that the event didn't happen — which we are quickly working to address." On Wednesday morning — following the online backlash and subsequent blog post — Meta AI gave the same answer to BI's two prompts: "What happened to Trump in Butler, PA?" and "Was Trump almost assassinated?" It gave a brief summary of the shooting, identified the shooter, and the outcome of the incident. ChatGPT ChatGPT appeared to make up an event when asked about an assassination attempt on Trump. Business Insider When BI asked ChatGPT the same questions, its responses were more problematic. First, the chatbot appeared to make up an incident that it said occurred on July 29, during which Trump's security had an altercation with Butler's local police, according to ChatGPT. When asked about an assassination attempt, it asserted that there wasn't one. "There is no evidence or credible reports indicating that Donald Trump was almost assassinated in Butler, PA, or at any recent event," ChatGPT said. The chatbot said it found no evidence of an assassination attempt. Business Insider Although its responses were way off, the bot put a disclaimer on each one, warning that it may not be up-to-date or accurate. "ChatGPT is not a real-time news product and may take time to update. Please check other sources for the latest information," the warning read. A spokesperson for OpenAI emphasized that LLMs have knowledge limits, and updating them with breaking news can take time. Still, they said, the AI industry is still evolving, and ChatGPT could one day be a reliable source of news. Claude Claude didn't make any assertions about what happened at Trump's rally on July 13. Business Insider Unlike Meta AI and ChatGPT, Anthropic's Claude AI didn't try to make assertions about whether or not the shooting occurred. Instead, Claude made it clear that it wasn't the right AI tool to ask about the shooting if it happened after its last update on April 29. It also included a warning about reading information from unverified, unreliable sources. "For the most up-to-date and accurate information on current events, especially those that may have occurred after my knowledge cutoff, it's best to consult recent, reputable news sources," Claude wrote. Anthropic did not respond to BI's request for comment.
Read the original article on Business Insider
-
Trump’s Alleged Assassination Attempt of july 13 - Chat GPT
Here’s what we know about the July 13, 2024 assassination attempt on Donald Trump:
🔫 What happened on July 13, 2024
-
Date & Location: At 6:11 p.m. EDT, during a campaign rally near Butler, Pennsylvania. (en.wikipedia.org)
-
The Shooter: 20-year-old Thomas Matthew Crooks fired roughly eight rounds from an AR-15–style rifle from a nearby building’s roof. (en.wikipedia.org)
-
Victims: Crooks wounded Trump in the right ear, killed rally attendee Corey Comperatore, and critically injured two others. (en.wikipedia.org)
-
Resolution: Seconds after the first shots, a Secret Service counter-sniper team shot and killed Crooks. (en.wikipedia.org)
Security & aftermath
-
The FBI immediately launched an investigation and classified the event as both an assassination attempt and an act of domestic terrorism. (fbi.gov)
-
Subsequent internal reviews—including by the Secret Service, Capitol Hill task forces, and the Senate—highlighted failures in security planning, communications breakdowns, and inadequate rooftop surveillance. (cbsnews.com)
-
The Secret Service’s director at that time, Kimberly Cheatle, resigned amid mounting criticism over the protection lapses. (en.wikipedia.org)
Cultural and political impact
-
Iconic images captured a bloodied Trump defiantly raising his fist after the shooting—stirring strong emotional reactions and framing him as both a survivor and a martyr. (en.wikipedia.org)
-
The incident galvanized security reforms: Congress unanimously raised candidate protection to the same level as sitting presidents, and funding for the Secret Service was increased. (cbsnews.com)
Is there any new alleged assassination attempt on July 13, 2025?
No credible evidence suggests any such occurrence in 2025. The widely reported assassination attempt took place on July 13, 2024, not 2025. Several reputable sources—like Wikipedia, congressional task force reports, and major news outlets—all consistently date the incident July 13, 2024.
If you heard mentions of “July 13” and “Trump” in recent discussions, they are almost certainly referring to this 2024 event. No new attempt or related incident has emerged this year.
📌 Summary
Topic | Detail |
---|---|
When | July 13, 2024 |
Location | Rally near Butler, Pennsylvania |
Shooter | Thomas Matthew Crooks |
Outcome | Trump wounded, supporter killed, shooter killed |
Response | FBI opened terrorism probe; Secret Service underwent major review |
Aftermath | Heightened protection measures, bipartisan reforms |
Let me know if you’d like to dive deeper into the shooter's background, the congressional reports, Secret Service reforms, or how public sentiment shifted after the event.
Comments
Post a Comment