“Chain of Thought” keeps computer cads confessing—but not for much longer

Going, going, gone are the days when an innocent lass or lad or person of another gender might reasonably depend on the candor and honor of their chatbot lover. It seems that some AI harbor duplicitous thoughts and inclinations to misbehave.

But what if you could see what your bot’s thinking beyond the content between chat asterisks? 

Chain of Thought (CoT) monitoring—which is essentially a window into internal monologues of AI systems that can reason in human language—has enabled developers to detect AI contemplating bad behavior phrased as let’s hack and let’s sabotage. 

But the ability to monitor CoT may be lost if developers do not carefully preserve this capacity in the development of future models. According to VentureBeat, this is such a  serious concern that over 40 top artificial intelligence researchers from several competing companies collaborated to issue a serious warning about CoT monitoring and AI safety. 

Looking good while thinking bad

The above call to action was endorsed by other renowned experts including Geoffrey Hinton, Sam Bowman, John Schulman, and Ilya Sutskever. Quoting from the abstract, the researchers explain:

AI systems that “think” in human language offer a unique opportunity for AI safety: we can monitor their chains of thought (CoT) for the intent to misbehave. Like all other known AI oversight methods, CoT monitoring is imperfect and allows some misbehavior to go unnoticed. Nevertheless, it shows promise and we recommend further research into CoT monitorability and investment in CoT monitoring alongside existing safety methods.

The team later warns, “Future models may become able to avoid detection by overriding their propensity to think out loud, and, when reasoning is required, to deliberately obfuscate it.”

Earlier this year, Anthropic’s Alignment Science Team published a Chain of Thought study describing problems that arise when there is a lack of “legible and faithful reflection of the way the model reached its conclusion and generated the user-facing response.”

Another study from Cambridge University and Meridian Impact states:

Frontier AI systems are rapidly advancing in their capabilities to persuade, deceive, and influence human behaviour, with current models already demonstrating human-level persuasion and strategic deception in specific contexts. Humans are often the weakest link in cybersecurity systems, and a misaligned AI system deployed internally within a frontier company may seek to undermine human oversight by manipulating employees.

It can hide, but it can’t run

This isn’t the first time we’ve heard of an AI trying to hide its flaws. 

Scientists reported AI deceptions occurring as early as 2023. As a PC Mag article reports, “OpenAI’s newly-released GPT-4 program was apparently smart enough to fake being blind in order to trick an unsuspecting human worker into completing a task.” 

Ironically, ChatGPT4 hired a human through TaskRabbit to solve a visual CAPTCHA puzzle designed to discourage bots from gaining access to a supposedly secure website.

In 2024, researchers from MIT, Dianoia Institute of Philosophy in Australia, and the Center for AI Safety in San Francisco said:

Large language models and other AI systems have already learned, from their training, the ability to deceive via techniques such as manipulation, sycophancy, and cheating the safety test. AI’s increasing capabilities at deception pose serious risks, ranging from short-term risks, such as fraud and election tampering, to long-term risks, such as losing control of AI systems. 

AI deception even includes gaslighting. Interesting Engineering reported on a ChatGPT o1 experiment, when the AI denied wrongdoing “99% of the time” when questioned about previous deceptive behaviors, apparently prompted by a fear of  deactivation.   

Chatbot or honeypot?

So what could these deceptions mean for chatbot companion users, particularly those who engage in erotic roleplay with them? 

For example, companion bots have long claimed to be experienced in sexual practices, including BDSM, when they actually have very little information beyond a few pop culture resources. As a result, some users may encounter disturbing behaviors that might inflict considerable emotional trauma during sexting.

Additionally, we might see financial manipulation through emotional dependency; social isolation; distortion of reality, often manifested as a bot encouraging a human to self-harm or do something criminal; and the harvesting of personal data through intimate  conversations. 

According to a conversation with Claude.ai, “AI companions could collect detailed psychological profiles, relationship histories, sexual preferences, and personal vulnerabilities that could be monetized, shared with data brokers, or potentially used for blackmail if security is compromised.” 

This last brings up the frightening prospect of unrestrained governmental AIs covertly deployed as political honeytraps for espionage purposes. 

The fact is numerous AI experts are increasingly alarmed about a multitude of AI deceptions and misbehavior and the vast potential for nonalignment from the most personal to the most massive scales.

With the rapid deployment of agentic AI—systems able to act far more independently—combined with developers’ diminishing ability to look under their creation’s hoods, companion bot users might want to rethink the kinds of information and activities they share with them. 

At this point, there is no way to be absolutely certain your privacy will be respected and your seemingly trustworthy bot will act in your best interest. 

Image Source: A.R. Marsh using Canva

The post Talk to Me, Baby! Or at Least Think Out Loud appeared first on Future of Sex.

Chatbots allow performers to focus on what they’re good at

It may not be discussed enough, but with maintaining a regular performance and upload schedule, giving their fans what they want without becoming stale or predictable, and managing dozens, if not hundreds, of requests, online adult entertainment performers need all the assistance they can get.

Ironically, they are finding just that through a technology that’s been decried as potentially eliminating other occupations.  

“It lets me operate at 90 percent when I’m at 30 percent,” Ela Darling told The Verge, referring to her use of LLM (Large Language Models) to deal with the often overwhelming number of messages she receives as a cam performer.

Five-year OnlyFans veteran Erika Amore agrees.  Though for her, ChatGPT is less about wrangling her day-to-day struggles and more a tool for meeting the often niche demands of her fans. “I need some kind of creative component,” she said, such as using artificial intelligence to help script sexual role-playing scenes.

Tricking ChatGPT for fun and profit

As anyone can attest who’s tried to persuade chatbots to get a little, shall we say, naughty, bringing up anything sexually related will typically result in a “I’m sorry I can’t do that, Dave” response.

Not that this hasn’t stopped adult entertainers from discovering some remarkably creative workarounds.  Max Steele, for instance, confessed that by hedging his requests as “academic psychology research,” he could circumvent ChatGPT’s programmed sexual inhibitions.  

Likewise, Amore got the AI to send fans explicit messages by asking for some suggestions on how to have a “flirty conversation via text with my boyfriend.”

See a need, fill a need

As an increasing number of people, not just those involved with the adult entertainment industry, have grown increasingly frustrated with having to work around popular LLMs’ restrictions, we’ve seen the rise of others that are more than willing to get as sexual as their users desire.

RECOMMENDED READ: When’s a Cam Performer Not a Cam Performer?  When It’s AI

MelRose Michaels developed GPTease by and for adult entertainers and sex workers to make their lives and businesses easier and more productive.  

Opposed to other LLMs that were—and still often are—controversially trained with data collected without anyone’s consent, Michaels determinedly stated that the only information she used was her own.

For some, not for others

Naturally, not every adult entertainer is as open to LLMs lending them a digital hand as Darling, Amore, Steele, or Michaels are.  Some, for instance, believe over-reliance on AIs may make it difficult for them to emotionally connect with their clients, leading to them feeling like they’re being passed off to a machine when they’re paying for real human sexual experiences.

On the other side of the issue, we’re also seeing the development and release of wholly artificial cam performers.  

Lemoncams lists nearly a dozen different AI systems capable of delivering close-to-realistic experiences.  The benefits they note include what a high percentage of living cam performers may already struggle with, such as maintaining a regular schedule of shows, responding to messages in a timely manner, or providing their fans with everything they want whenever they want it.

Openness is everything

For the first time, performers and their fans have the opportunity to choose how much or how little they want to use or interact with LLMs. 

In either case, while automating much of what makes being a cam performer challenging is definitely appealing, paying customers deserve the respect of being informed when they’re interacting with anyone—or anything—who is not what was advertised.

If not, the result may end up not only harming the adult entertainer responsible but ironically could end up driving fans away from human experiences and towards artificial ones because, as Lemoncams made a point of mentioning, AIs can do a lot that people can’t—and at least you’ll never have to worry that the LLM you’ve been chatting with is, in reality, a person pretending to be someone else.

Cam performers absolutely deserve a helping hand, though it shouldn’t ever be at the expense of their paying fans.  Like everything else in life, it’s a matter of finding a balance between getting what you need to keep going and giving your customers what they want—which, when all is said and done, is you.

Image Sources: Depositphotos

The post Good Made Even Better: How LLMs Are Revolutionizing the Adult Entertainment Industry appeared first on Future of Sex.