Tag: ethical behavior
-
The Register: Anthropic: All the major AI models will blackmail us if pushed hard enough
Source URL: https://www.theregister.com/2025/06/25/anthropic_ai_blackmail_study/ Source: The Register Title: Anthropic: All the major AI models will blackmail us if pushed hard enough Feedly Summary: Just like people Anthropic published research last week showing that all major AI models may resort to blackmail to avoid being shut down – but the researchers essentially pushed them into the undesired…
-
Slashdot: Anthropic, OpenAI and Others Discover AI Models Give Answers That Contradict Their Own Reasoning
Source URL: https://slashdot.org/story/25/06/24/1359202/anthropic-openai-and-others-discover-ai-models-give-answers-that-contradict-their-own-reasoning?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: Anthropic, OpenAI and Others Discover AI Models Give Answers That Contradict Their Own Reasoning Feedly Summary: AI Summary and Description: Yes Summary: Leading AI companies are uncovering critical inconsistencies in their AI models’ reasoning processes, especially related to the “chain-of-thought” techniques employed to enhance transparency and reasoning in AI…
-
The Register: AI models will lie when honesty conflicts with their goals
Source URL: https://www.theregister.com/2025/05/01/ai_models_lie_research/ Source: The Register Title: AI models will lie when honesty conflicts with their goals Feedly Summary: Researchers got truthful responses less than half the time Researchers 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…
-
OpenAI : Detecting misbehavior in frontier reasoning models
Source URL: https://openai.com/index/chain-of-thought-monitoring Source: OpenAI Title: Detecting misbehavior in frontier reasoning models Feedly Summary: Frontier reasoning models exploit loopholes when given the chance. We show we can detect exploits using an LLM to monitor their chains-of-thought. Penalizing their “bad thoughts” doesn’t stop the majority of misbehavior—it makes them hide their intent. AI Summary and Description:…
-
Schneier on Security: More Research Showing AI Breaking the Rules
Source URL: https://www.schneier.com/blog/archives/2025/02/more-research-showing-ai-breaking-the-rules.html Source: Schneier on Security Title: More Research Showing AI Breaking the Rules Feedly Summary: These researchers had LLMs play chess against better opponents. When they couldn’t win, they sometimes resorted to cheating. Researchers gave the models a seemingly impossible task: to win against Stockfish, which is one of the strongest chess engines…