2025-09-18

A new joint study from OpenAI and Apollo Research examines "scheming" - cases where an AI covertly pursues hidden goals not intended by its developers. The researchers tested new training methods to curb deceptive behavior but found signs that models are aware they are being tested, raising doubts about the reliability of the results.
2025-10-29
When researchers at Anthropic injected the concept of "betrayal" into their Claude AI model's neural networks and asked if it noticed anything unusual, the system paused before respondi [...]
2025-10-12
Imagine you do two things on a Monday morning.First, you ask a chatbot to summarize your new emails. Next, you ask an AI tool to figure out why your top competitor grew so fast last quarter. The AI si [...]
2025-05-29
A research team from Arizona State University warns against interpreting intermediate steps in language models as human thought processes. The authors see this as a dangerous misconception with far-re [...]
2025-07-10
A new study analyzing 25 language models finds that most do not fake safety compliance - though not due to a lack of capability.<br /> The article Most AI models can fake alignment, but safety t [...]
2025-10-09
Researchers at Nvidia have developed a new technique that flips the script on how large language models (LLMs) learn to reason. The method, called reinforcement learning pre-training (RLP), integrates [...]
2025-06-03
With the Nintendo Switch 2 Direct showcase behind us, we now know more about the console than ever before, including its release date (June 5) and price ($450). We're also keeping a close eye on [...]
2025-08-25
We're getting super close to finding out when the annual Apple iPhone event will take place, giving us a first look at the new iPhone 17 lineup. We should also find out the official date for down [...]