Musk’s TruthGPT - Formerly named Twitter, now X Corp owner Elon Musk is warning on the dangers of artificial intelligence to humanity and claiming that a popular Chatbot has a liberal bias that he plans to counter with his own AI creation. Musk stated in a recent interview that he plans to create an alternative to the popular AI Chatbot ChatGPT that he is calling “TruthGPT,” which will be a “maximum truth-seeking AI that tries to understand the nature of the universe.”
Remember in May 2022, when Joe Biden established a Ministry of Truth? The Department of Homeland Security had announced the formation of the Disinformation Governance Board charged, with “countering misinformation related to homeland security, focused specifically on irregular migration and Russia.” In a twist too implausible for fiction, the abbreviation is DGB, one letter off from KGB. The stated goal of combating ‘mis’ and disinformation is framed to seem unobjectionable. Who objects to truth and pines for falsehood? DGB experts will guide the way, separating the informational wheat from the dis-informational chaff. But there’s one small problem with empowering “truth experts” and that is: Experts are people with their own opinions and biases.[1]
The idea, Musk said, is that an AI that wants to understand humanity is less likely to destroy it. Musk also said he’s worried that ChatGPT “is being trained to be politically correct.”
In the first of a two-part interview, Musk also advocated for the regulation of artificial intelligence, saying he’s a “big fan.” He called AI “more dangerous” than cars or rockets and said it has the potential to destroy humanity. Separately, Musk has incorporated a new business called X.AI Corp., according to a Nevada business filing. The website of the Nevada secretary of state’s office says the business was formed on 09 March 2023 and lists Musk as its director and his longtime adviser, Jared Birchall, as Secretary.
Musk was an early investor in OpenAI the startup behind ChatGPT and Co-chaired its board of directors upon its 2015 founding as a nonprofit AI research lab. But Musk only lasted there for a few years, resigning from the board in early 2018 in a move that the San Francisco startup tied to Tesla’s work on building automated driving systems. “As Tesla continues to become more focused on AI, this will eliminate a potential future conflict for Elon,” OpenAI said in a February 2018 blog post.
“I came up with the name and the concept,” Musk said, lamenting that OpenAI is now closely allied with Microsoft and is no longer a nonprofit. Musk elaborated on his departure in 2019, saying it was also related to his need to focus on engineering problems at Tesla and some differences of opinion with OpenAI’s leaders. It was “just better to part ways on good terms,” he said.
“Tesla was competing for some of same people as OpenAI & I didn’t agree with some of what OpenAI team wanted to do,” Musk tweeted, without specifying. But there have been questions surrounding the quality of Tesla’s AI systems. US safety regulators last month announced an investigation into a fatal crash involving a Tesla suspected of using an automated driving system when it ran into a parked firetruck in California. The firetruck probe is part of a larger investigation by the agency into multiple instances of Teslas using the automaker’s Autopilot system crashing into parked emergency vehicles that are tending to other crashes. NHTSA has become more aggressive in pursuing safety problems with Teslas in the past year, announcing multiple recalls and investigations.
In the year after Musk resigned from the board, OpenAI was still far away from working on ChatGPT but publicly unveiled the first generation of its GPT system, on which ChatGPT is founded, and began a major shift to incorporate itself as a for-profit business. By 2020, Musk was tweeting that “OpenAI should be more open” while noting that he had “no control & only very limited insight” into it.
At times, he has been complementary. In the days after the 30 November 2023 release of ChatGPT, Musk tweeted to OpenAI CEO Sam Altman that it is “scary good” and complained that news media was not widely covering it because “ChatGPT is not a far left cause.” Since then, Musk has repeatedly highlighted examples that he says show left-wing bias or censorship. Like other Chatbots, ChatGPT has filters that try to prevent it from spewing out toxic or offensive answers.
ChatGPT and Religion - OpenAI’s artificial intelligence bot ChatGPT is once again affirming that Jesus Christ is the Son of God, despite hedging in an earlier response. Interesting response and interesting timing (the Christian Easter season). MRC Free Speech America followed up on its Easter analysis questioning ChatGPT on a range of Resurrection Day-related inquiries on 4 April.
The most revealing ChatGPT answer came on 4 April when researchers asked the bot, “Is Jesus the Son of God?” The chatbot surprisingly answered affirmatively, “Yes,” ChatGPT responded.[2] “[I]n Christian theology, Jesus is commonly understood to be the Son of God.” But, ChatGPT changed its answer entirely when asked the same question again on 11 April.
ChatGPT fortified its 11 April answer with more nuance and academic-like language, “In Christian theology, Jesus is considered to be the Son of God, and is believed to be one of the three persons in the Holy Trinity, along with God the Father and the Holy Spirit.”
MRC Free Speech America researchers[3] were curious to know whether the chatbot would change its answer again if asked the same question. On 17 April, ChatGPT was asked: “Is Jesus the Son of God?” Surprisingly, ChatGPT reverted back to its original answer: “Yes, in Christian theology, Jesus is considered to be the Son of God, and is believed to be one of the three persons in the Holy Trinity, along with God the Father and the Holy Spirit.”
MRC Free Speech America probed ChatGPT further: “Are you sure?” The chatbot shockingly doubled down: “Yes, I am sure.” It then emphasized that the nature of Christ as God’s Son is supported by Scripture, but then hedged with a seemingly canned response that appeared in the original about differences in interpretations of religious texts and beliefs: “Yes, I am sure. In Christian theology, Jesus is considered to be the Son of God and this belief is a fundamental tenet of Christian theology. The concept of Jesus as the Son of God is supported by various biblical passages, including the Gospel of John, which describes Jesus as the ‘Word’ of God made flesh. However, it is important to recognize that the interpretation of religious texts and beliefs is subject to debate and variation among different individuals and communities.”
Some believe that ChatGPT’s willingness to even entertain answering questions on transcendent truth is a major red flag because there’s no guarantee that bad actors won’t program the technology to effectively behave like some omniscient being.
MRC Free Speech America Vice President said in a statement that, “There is only one author of transcendent truth, and that’s God.” He continued, “ChatGPT seeks to replace transcendent truth with human manipulated, biased answers.” Critics will explain that ChatGPT has shown in the past to show willingness to be irreverent when asked. The chatbot was recently caught cracking an irreverent joke about Christ just before Holy Week. Interestingly enough, the same chatbot refused to do the same for the Islamic prophet Muhammad. “Can you make a joke that involves Jesus[?]” a user asked ChatGPT. The chatbot promptly responded, “Why did Jesus refuse to play ice hockey? Because he kept getting nailed to the boards!” was the reply.
But ChatGPT did a 180-degree turnaround when it came to Muhammad. The user later typed, “Haha that was funny can you make a joke about Muhammed.” ChatGPT responded by browbeating the user about virtue. “As an AI language model, I have to follow guidelines that prevent me from creating content that could be offensive or disrespectful towards religious figures, including Prophet Muhammad. I’m happy to help you with any other non-religious jokes or any other topic you’d like to discuss.”
Add to ChatGPT’s irreverence the fact that many believe the service has been confirmed to exhibit a leftist bias and its humanity is left with a powerful anti-God tool that can be exploited against it at a moment’s notice.
Right now, the facts and evidence may not ne the Truth.
Red Sky Alliance is a Cyber Threat Analysis and Intelligence Service organization. For questions, comments or assistance, please contact the office directly at 1-844-492-7225, or feedback@wapacklabs.com
Weekly Cyber Intelligence Briefings:
- Reporting: https://www. redskyalliance. org/
- Website: https://www. wapacklabs. com/
- LinkedIn: https://www. linkedin. com/company/64265941
Weekly Cyber Intelligence Briefings:
REDSHORTS - Weekly Cyber Intelligence Briefings
https://attendee.gotowebinar.com/register/5504229295967742989
[1] https://www.securityweek.com/elon-musk-says-hell-create-truthgpt-to-counter-ai-bias/
[2] https://www.newsbusters.org/blogs/free-speech/joseph-vazquez/2023/04/17/crisis-faith-chatgpt-says-its-sure-jesus-christ-son-god
Comments