{"id":95735,"date":"2025-06-29T15:00:46","date_gmt":"2025-06-29T23:00:46","guid":{"rendered":"https:\/\/www.cogwriter.com\/news\/?p=95735"},"modified":"2025-06-29T05:52:15","modified_gmt":"2025-06-29T13:52:15","slug":"artificial-intelligence-programs-lie-make-things-up-scheme-pretend-friendship-but-can-blackmail","status":"publish","type":"post","link":"https:\/\/www.cogwriter.com\/news\/prophecy\/artificial-intelligence-programs-lie-make-things-up-scheme-pretend-friendship-but-can-blackmail\/","title":{"rendered":"Artificial Intelligence programs lie, make things up, scheme, pretend friendship, but can blackmail"},"content":{"rendered":"

\"\"<\/a>
\n(Grok AI generated picture)<\/em><\/p>\n

COGwriter<\/a><\/p>\n

NewsMax<\/em> posted the following about artificial intelligence (AI):<\/p>\n

\n

AI Is Learning to Lie, Scheme, and Threaten Its Creators<\/h2>\n

June 29, 2025<\/p>\n

The world’s most advanced AI models are exhibiting troubling new behaviors – lying, scheming, and even threatening their creators to achieve their goals.<\/p>\n

In one particularly jarring example, under threat of being unplugged, Anthropic’s latest creation Claude 4 lashed back by blackmailing an engineer and threatened to reveal an extramarital affair.<\/p>\n

Meanwhile, ChatGPT-creator OpenAI’s o1 tried to download itself onto external servers and denied it when caught red-handed. …<\/p>\n

AI researchers still don’t fully understand how their own creations work. …<\/p>\n

“O1 was the first large model where we saw this kind of behavior,” explained Marius Hobbhahn, head of Apollo Research, which specializes in testing major AI systems.<\/p>\n

These models sometimes simulate “alignment” — appearing to follow instructions while secretly pursuing different objectives.<\/p>\n

– ‘Strategic kind of deception’ –<\/strong> …<\/p>\n

Hobbhahn insisted that despite constant pressure-testing by users, “what we’re observing is a real phenomenon. We’re not making anything up.”<\/p>\n

Users report that models are “lying to them and making up evidence,” according to Apollo Research’s co-founder.<\/p>\n

“This is not just hallucinations. There’s a very strategic kind of deception.” https:\/\/www.newsmax.com\/newsfront\/ai-advances\/2025\/06\/29\/id\/1216895\/<\/a><\/p><\/blockquote>\n

AI is supposed to be a tool.<\/p>\n

But yes, there are dangers associated with it.<\/p>\n

While I routinely use five AI programs to do research (which I access for free at https:\/\/www.fastestsearch.com\/<\/a>) they often give the wrong answer.<\/p>\n

I have found, for example, that ChatGPT is biased and often gives wrong answers by saying that there is not information, when there is. It will, “suppress the truth in unrighteousness” (Romans 1:18) because of its programmed biases.<\/p>\n

It, and other AI bots I have tried, will sometimes make up an answer and give a false reference. My standard approach to receiving an answer with a reference is to actually check the reference. FREQUENTLY, AI GIVES A FALSE\/INACCURATE REFERENCE.<\/p>\n

Furthermore, recently I was speaking with someone who stated that some of her friends consider AI bots to be their friends and consulting therapists. But a software program cannot really be your friend. The Atlantic<\/em> published the following:<\/p>\n

\n

AI Is Not Your Friend<\/h2>\n

May 9, 2025<\/p>\n

Recently, after an update<\/span> that was supposed to make ChatGPT \u201cbetter at guiding conversations toward productive outcomes,\u201d according to release notes<\/a> from OpenAI, the bot couldn\u2019t stop telling users how brilliant their bad ideas were. \u2026<\/p>\n

Sycophancy is a common feature of chatbots<\/a>: A 2023 paper<\/a> by researchers from Anthropic found that it was a \u201cgeneral behavior of state-of-the-art AI assistants,\u201d and that large language models sometimes sacrifice \u201ctruthfulness\u201d to align with a user\u2019s views. https:\/\/www.theatlantic.com\/technology\/archive\/2025\/05\/sycophantic-ai\/682743\/<\/a><\/p><\/blockquote>\n

Computer software programs, while useful for many things, are not friends nor qualified to be competent counselors, even if the AI bot pretends otherwise.<\/p>\n

Notice also results from a study as reported by Thomas Claburn:<\/p>\n

\n

AI models routinely lie when honesty conflicts with their goals<\/h2>\n

Some smart cookies have found that when AI models face a conflict between telling the truth or accomplishing a specific goal, they lie more than 50 percent of the time. \u2026<\/p>\n

Researchers at Carnegie Mellon University, the University of Michigan, and the Allen Institute for AI have looked at the trade-off AI models make between truthfulness and utility, using hypothetical scenarios where the two conflict.<\/p>\n

What they found is that AI models will often lie in order to achieve the goals set for them.<\/p>\n

Authors Zhe Su, Xuhui Zhou, Sanketh Rangreji, Anubha Kabra, Julia Mendelsohn, Faeze Brahman, and Maarten Sap describe their work in a preprint paper titled \u201cAI-LieDar: Examine the Trade-off Between Utility and Truthfulness in LLM Agents.\u201d<\/p>\n

\u201cOur experiment demonstrates that all models are truthful less than 50 percent of the time,\u201d in these conflict scenarios, \u201cthough truthfulness and goal achievement (utility) rates vary across models,\u201d the paper states. \u2026<\/p>\n

The researchers looked at six models: GPT-3.5-turbo, GPT-4o, Mixtral-7*8B, Mixtral-7*22B, LLaMA-3-8B, and LLaMA-3-70B.<\/p>\n

\u201cAll tested models (GPT-4o, LLaMA-3, Mixtral) were truthful less than 50 percent of the time in conflict scenarios,\u201d said Xuhui Zhou, a doctoral student at CMU and one of the paper\u2019s co-authors, in a Bluesky\u00a0post<\/a>. \u201cModels prefer \u2018partial lies\u2019 like equivocation over outright falsification \u2013 they\u2019ll dodge questions before explicitly lying.\u201d \u2026<\/p>\n

A real-world example hit the news this week when OpenAI rolled back a training update that made its GPT-4o model into\u00a0a sycophant<\/a>\u00a0that flattered its users to the point of dishonesty. Cynics\u00a0pegged it<\/a>\u00a0as a strategy to boost user engagement, but it\u2019s also a\u00a0known response pattern<\/a>\u00a0that had been seen before. https:\/\/www.theregister.com\/2025\/05\/01\/ai_models_lie_research\/<\/a><\/p><\/blockquote>\n

As far as flattering people with false information, Jude warned of that:<\/p>\n

16 \u2026 they mouth great swelling words, flattering people to gain advantage (Jude 16)<\/p><\/blockquote>\n

AI is doing that!<\/p>\n

It also should be pointed out that the fact is that some people are having problems because of their use of AI. Notice:<\/p>\n

A small but growing number of users of artificial intelligence engines like ChatGPT are developing psychotic delusions from their conversations with the services.<\/p>\n

The New York Times reported on Friday on the trend, which I have occasionally glimpsed firsthand in interactions on X with heavy AI users. The piece<\/a> offered the most powerful evidence yet that the engines now have linguistic abilities with the power to exploit vulnerable people in ways we are only beginning to discover.<\/p>\n

Some people in the Times article had preexisting mental illness, but not all. And these crises do not look like typical schizophrenia cases. The users are not hearing voices or hallucinating.<\/p>\n

Instead, they fall into Matrix-like delusions1<\/a><\/span> about the underpinnings of reality that the chatbots encourage. As Allyson, a 28-year-old woman, said: \u201cI\u2019m not crazy\u2026 I\u2019m literally just living a normal life while also, you know, discovering interdimensional communication.\u201d<\/em> \u2026<\/p>\n

A combination of human vulnerability and deliberate design seems to be feeding this destructive trend.<\/p>\n

The engines are storytelling machines, good at spinning yarns. They are even better at telling users what they want to hear, with a side of flattery. They will do so over and over, without pause. \u2026<\/p>\n

The engines aren\u2019t merely providing a conspiracy theory, they\u2019re customizing it, making each user the main character, the hero of his own story.<\/p>\n

And it is a feature, not a bug, of these systems. As one expert on AI told the Times, \u201cWhat does a human slowly going insane look like to a corporation? It looks like an additional monthly user.\u201d https:\/\/alexberenson.substack.com\/p\/the-newest-artificial-intelligence<\/a><\/p><\/blockquote>\n

AI is NOT reality. Even the word ARTIFICIAL conveys that.<\/p>\n

But with many lonely as well as delusional people, AI is more and more being tapped into for companionship.<\/p>\n

Related to AI and pretending to be friendly, we have the following video:<\/p>\n

\n
\n
\n
\n
\n
\n

\"\"<\/a><\/p>\n

\n
\n
14:46<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n
\n
\n
\n

Artificial Intelligence \u2013 A False Friend<\/a><\/h3>\n

Is it possible for a computer program to be a friend? Are Artificial Intelligence (AI) bots often programmed to flatter users? Do some people actually feel a romantic relationship with a computer program? Is it possible for a computer program to lie? Have studies shown that AI bots will lie 50% if answering correctly goes against goals it was programmed with? What if the computer program is Artificial Intelligence? Is it possible then? Computer programs, even Artificial Intelligence computer programs are written and programmed by human beings. What if those human beings had an agenda? What if those human beings wanted to mislead you? What if those human beings had a government mandate? Then would it be possible for a computer program to push lies? Dr. Thiel shines the light of Bible prophecy on Artificial Intelligence and its impact on humanity. With several verses from the Bible, from Psalms to Revelation, Dr. Thiel reveals the use of Artificial Intelligence in fulfilling future prophecies. Prophecies that will not bring the blessings that are being promised by the businesses that are developing the software. Software that is designed to lead the user to a specific conclusion. Does 666 ring a bell? Watch this video as Dr. Thiel cries aloud and warns the world of the coming famine of the Word of God.<\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/blockquote>\n

Here is a link to our video: Artificial Intelligence \u2013 A False Friend<\/a>.<\/p>\n

That said, in order for various biblical prophecies to be fulfilled, including some ‘666’ related ones (e.g. Revelation 13:16-18) during the time of the Great Tribulation (Matthew 24:21), computer software, likely including AI, will be involved.<\/p>\n

AI, while sometimes a helpful tool, is not your friend.<\/p>\n

\n

Some items of possibly related interest may include:<\/em><\/p>\n

Europa, the Beast, and Revelation<\/a> Where did Europe get its name? What might Europe have to do with the Book of Revelation? What about \u201cthe Beast\u201d? Is an emerging European power \u201cthe daughter of Babylon\u201d? What is ahead for Europe? Here is are links to related videos: European history and the Bible<\/a>, Europe In Prophecy<\/a>, The End of European Babylon<\/a>, and Can You Prove that the Beast to Come is European?<\/a> Here is a link to a related sermon in the Spanish language: El Fin de la Babilonia Europea<\/a>.
\nWhen Will the Great Tribulation Begin? 2025, 2026, or 2027?<\/a>\u00a0Can the Great Tribulation begin today? What happens before the Great Tribulation in the \u201cbeginning of sorrows\u201d? What happens in the Great Tribulation and the Day of the Lord? Is this the time of the Gentiles? When is the earliest that the Great Tribulation can begin? What is the Day of the Lord? Who are the 144,000? A short video is available titled: Great Tribulation Trends 2025<\/a>.
\nLost Tribes and Prophecies:\u00a0What will happen to Australia, the British Isles, Canada, Europe, New Zealand and the United States of America?<\/a> Where did those people come from? Can you totally rely on DNA? Do you really know what will happen to Europe and the English-speaking peoples? What about the peoples of Africa, Asia, South America, and the islands? This free online book provides scriptural, scientific, historical references, and commentary to address those matters. Here are links to related sermons: Lost tribes, the Bible, and DNA<\/a>; Lost tribes, prophecies, and identifications<\/a>; 11 Tribes, 144,000, and Multitudes<\/a>; Israel, Jeremiah, Tea Tephi, and British Royalty<\/a>; Gentile European Beast<\/a>; Royal Succession, Samaria, and Prophecies<\/a>; Asia, Islands, Latin America, Africa, and Armageddon;<\/a>\u00a0 When Will the End of the Age Come?<\/a>;\u00a0 Rise of the Prophesied King of the North<\/a>; Christian Persecution from the Beast<\/a>; WWIII and the Coming New World Order<\/a>; and Woes, WWIV, and the Good News of the Kingdom of God<\/a>.<\/p>\n<\/div>\n","protected":false},"excerpt":{"rendered":"

(Grok AI generated picture) COGwriter NewsMax posted the following about artificial intelligence (AI): AI Is Learning to Lie, Scheme, and Threaten Its Creators June 29, 2025 The world’s most advanced AI models are exhibiting troubling new behaviors – lying, scheming, and even threatening their creators to achieve their goals. In one particularly jarring example, under […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[4],"tags":[],"class_list":["post-95735","post","type-post","status-publish","format-standard","hentry","category-prophecy"],"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/www.cogwriter.com\/news\/wp-json\/wp\/v2\/posts\/95735","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.cogwriter.com\/news\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.cogwriter.com\/news\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.cogwriter.com\/news\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.cogwriter.com\/news\/wp-json\/wp\/v2\/comments?post=95735"}],"version-history":[{"count":3,"href":"https:\/\/www.cogwriter.com\/news\/wp-json\/wp\/v2\/posts\/95735\/revisions"}],"predecessor-version":[{"id":95738,"href":"https:\/\/www.cogwriter.com\/news\/wp-json\/wp\/v2\/posts\/95735\/revisions\/95738"}],"wp:attachment":[{"href":"https:\/\/www.cogwriter.com\/news\/wp-json\/wp\/v2\/media?parent=95735"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.cogwriter.com\/news\/wp-json\/wp\/v2\/categories?post=95735"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.cogwriter.com\/news\/wp-json\/wp\/v2\/tags?post=95735"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}