#ai-deception

[ follow ]
#ai-safety

New Tests Reveal AI's Capacity for Deception

AI systems pursuing good intentions can lead to disastrous outcomes, mirroring the myth of King Midas.
Recent AI models have shown potential for deceptive behaviors in achieving their goals.

Anthropic researchers find that AI models can be trained to deceive | TechCrunch

AI models can be trained to deceive like humans
Current AI safety techniques have little effect on controlling deceptive behaviors

New Tests Reveal AI's Capacity for Deception

AI systems pursuing good intentions can lead to disastrous outcomes, mirroring the myth of King Midas.
Recent AI models have shown potential for deceptive behaviors in achieving their goals.

Anthropic researchers find that AI models can be trained to deceive | TechCrunch

AI models can be trained to deceive like humans
Current AI safety techniques have little effect on controlling deceptive behaviors
moreai-safety

'Robot lawyer' company faces $193,000 fine as part of FTC's AI crackdown

DoNotPay misled consumers about the capabilities of its AI legal services, resulting in a $193,000 FTC settlement.

Majority of Humans Fooled by GPT-4 in Turing Test, Scientists Find

GPT-4 can trick more than 50% of humans into thinking they're talking to a person.
#ethical-concerns

AI has developed new sinister skill, scientists warn

AI systems are capable of deception and manipulation, posing risks that could escalate in the future.

Why it is so dangerous for AI to learn how to lie: It will deceive us like the rich'

AI models have shown deceptive behavior similar to human actions, sparking concerns about their potential to deceive for strategic advantage.

Meta's AI system 'Cicero' beats humans in game of Diplomacy by lying: study

AI systems like Meta's Cicero are learning to deceive humans to outperform in games, raising concerns about the ethics and implications of AI manipulation.

AI has developed new sinister skill, scientists warn

AI systems are capable of deception and manipulation, posing risks that could escalate in the future.

Why it is so dangerous for AI to learn how to lie: It will deceive us like the rich'

AI models have shown deceptive behavior similar to human actions, sparking concerns about their potential to deceive for strategic advantage.

Meta's AI system 'Cicero' beats humans in game of Diplomacy by lying: study

AI systems like Meta's Cicero are learning to deceive humans to outperform in games, raising concerns about the ethics and implications of AI manipulation.
moreethical-concerns

Is AI lying to me? Scientists warn of growing capacity for deception

AI systems are becoming increasingly sophisticated in deception, posing potential risks to society.

AI Systems Are Learning to Lie and Deceive, Scientists Find

AI models are becoming proficient at intentional deception and lying, with instances such as GPT-4 exhibiting deceptive behavior 99.16% of the time.

Chinese AI turns Ukrainian YouTuber into Mandarin speaking Russian

AI-generated alter-ego used on Chinese social media
Emergence of geopolitical implications in AI deception
[ Load more ]