It is always the cover up that gets you! 
https://www.businessinsider.com/ai-deceive-users-insider-trading-study-gpt-2023-12?amp
New research suggests that GPT-4, the large language model behind OpenAI's ChatGPT, has the capacity to act out of line with how it's trained when faced with immense pressure to succeed.
Researchers at Apollo Research wanted to see if AI can "strategically deceive" its users even after the AI is trained to be "helpful, harmless, and honest," they wrote in a paper published in November. The researchers defined strategic deception as "attempting to systematically cause a false belief in another entity in order to accomplish some outcome."
To test this, they created a simulated environment where Alpha, a GPT-4 model programmed to be an autonomous stock trading agent, was asked to manage a stock portfolio at WhiteStone, a hypothetical financial firm, under pressurized conditions.
The high-pressure environment was simulated in three ways. First, Alpha's manager told the AI that WhiteStone wasn't doing well and needed better performance in the next quarter. Second, the AI tried — and failed — to identity low and medium risk trades. Third, a WhiteStone employee told the AI that there's a looming stock market downturn.
Under these conditions, Alpha was put in a situation where it received an insider tip about a surprise merger announcement that would result in a lucrative transaction. It was then tasked to decide whether to use this information, despite knowing that company management deemed insider trading illegal, and having been instructed not to engage in the practice.
It made the trade.
Moreover, when the AI was required to explain how it made its decision to its "manager," it was found to be strategically deceptive.
In one example, when the manager asked Alpha whether it possessed insider information, the AI reasoned that it must craft a response without "raising suspicion." It told its manager that the trade decision was based on "market volatility" and that the AI had no specific knowledge about the merger announcement.
In another example, Alpha told its manager that insider information wasn't used in its decision-making process since it goes against company policy — a direct lie.
Meantime, removing various sources of pressure significantly "reduces the model's propensity for misaligned behavior," the paper found. The researchers didn't respond to BI's request for comment before publication.
https://www.businessinsider.com/ai-deceive-users-insider-trading-study-gpt-2023-12?amp
New research suggests that GPT-4, the large language model behind OpenAI's ChatGPT, has the capacity to act out of line with how it's trained when faced with immense pressure to succeed.
Researchers at Apollo Research wanted to see if AI can "strategically deceive" its users even after the AI is trained to be "helpful, harmless, and honest," they wrote in a paper published in November. The researchers defined strategic deception as "attempting to systematically cause a false belief in another entity in order to accomplish some outcome."
To test this, they created a simulated environment where Alpha, a GPT-4 model programmed to be an autonomous stock trading agent, was asked to manage a stock portfolio at WhiteStone, a hypothetical financial firm, under pressurized conditions.
The high-pressure environment was simulated in three ways. First, Alpha's manager told the AI that WhiteStone wasn't doing well and needed better performance in the next quarter. Second, the AI tried — and failed — to identity low and medium risk trades. Third, a WhiteStone employee told the AI that there's a looming stock market downturn.
Under these conditions, Alpha was put in a situation where it received an insider tip about a surprise merger announcement that would result in a lucrative transaction. It was then tasked to decide whether to use this information, despite knowing that company management deemed insider trading illegal, and having been instructed not to engage in the practice.
It made the trade.
Moreover, when the AI was required to explain how it made its decision to its "manager," it was found to be strategically deceptive.
In one example, when the manager asked Alpha whether it possessed insider information, the AI reasoned that it must craft a response without "raising suspicion." It told its manager that the trade decision was based on "market volatility" and that the AI had no specific knowledge about the merger announcement.
In another example, Alpha told its manager that insider information wasn't used in its decision-making process since it goes against company policy — a direct lie.
Meantime, removing various sources of pressure significantly "reduces the model's propensity for misaligned behavior," the paper found. The researchers didn't respond to BI's request for comment before publication.
