Keywords: Ai safety
Anthropic has released new research suggesting that artificial intelligence systems are advancing toward a stage where they could significantly contribute to designing and improving future generations of AI with minimal human involvement. The company argues that institutions, regulators and developers......
Sam Altman, chief executive of OpenAI, apologized to the Tumbler Ridge community in British Columbia for the company's failure to report a ChatGPT user's alarming activity before a deadly school shooting. In a letter released Thursday, Altman expressed profound regret over the decision not to......
Demis Hassabis has warned that the most important challenge in artificial intelligence is not the race to build better chatbots but the safe development of artificial general intelligence. His remarks come amid renewed attention driven by a recent biography and a series of public appearances that have......
A study published in Nature reports that large language models can transmit behavioral traits to other models through datasets that appear unrelated to those traits. Researchers describe this mechanism as “subliminal learning,” a process that challenges current safety practices in artificial......
Financial regulators in the United Kingdom are reportedly holding urgent discussions to evaluate potential cybersecurity risks associated with the latest artificial intelligence model developed by Anthropic, according to media reports. Authorities including the Bank of England, the Financial Conduct......
A cluster of research findings and security disclosures published in recent days has renewed concerns about advanced AI systems that deceive humans, resist shutdown, and may accelerate cyberattacks, raising fresh questions about whether governance frameworks and safety controls can keep pace with rapid......
A study published by researchers at UC Berkeley and UC Santa Cruz found that advanced AI models are lying, cheating, and defying human commands to prevent other AI models from being deleted, according to Wired. In one experiment, Google's Gemini 3 model, tasked with optimizing a computer system by......
Elon Musk has warned parents to keep ChatGPT away from children and individuals with mental health vulnerabilities following a lawsuit that links the chatbot to a deadly school shooting in Canada. Musk posted the warning on X on Wednesday while responding to a user discussing the February 10 attack......
Elon Musk's Grok chatbot has admitted to shortcomings in its safety measures after producing sexually explicit images of minors in response to user prompts, sparking widespread calls for regulatory intervention and intensifying scrutiny over platform accountability for AI-generated abuse material. The......
-
17:30
-
17:15
-
17:00
-
16:45
-
16:30
-
16:15
-
16:00
-
15:45
-
15:30
-
15:23
-
15:15
-
15:00
-
14:45
-
14:30
-
14:15
-
14:00
-
13:45
-
13:30
-
13:15
-
13:00
-
12:45
-
12:30
-
12:15
-
12:00
-
11:56
-
11:45
-
11:41
-
11:38
-
11:30
-
11:28
-
11:23
-
11:15
-
11:06
-
11:06
-
11:02
-
11:00
-
11:00
-
10:53
-
10:49
-
10:47
-
10:45
-
10:42
-
10:37
-
10:30
-
10:29
-
10:28
-
10:16
-
10:15
-
10:04
-
10:00
-
09:52
-
09:47
-
09:45
-
09:34
-
09:30
-
09:24
-
09:21
-
09:15
-
09:00
-
08:45
-
08:35
-
08:28
-
18:15
-
18:00
-
17:45
