A new, challenging AGI test stumps most AI models
The Arc Prize Foundation has a new test for AGI that leading AI models from Anthropic, Google, and DeepSeek score poorly on.
A new AI test is outwitting OpenAI, Google models, among others
Google, OpenAI, DeepSeek, et al. are nowhere near achieving AGI (Artificial General Intelligence), according to a new ...
New Scientist on MSN6h
Leading AI models fail new test of artificial general intelligence
A new test of AI capabilities consists of puzzles that humans are able to solve without too much trouble, but which all ...
Chatbots Are Cheating on Their Benchmark Tests
To measure the success of their work, companies cite industry-standard benchmark tests whenever they release a new model. The tests supposedly contain questions the models haven’t seen, showing that ...
Hosted on MSN1mon
AI reaches human-level performance on general intelligence test—what does it mean?
model has just achieved human-level results on a test designed to measure “general intelligence”. On December 20, OpenAI’s o3 system scored 85% on the ARC-AGI benchmark, well above the ...
China is on the brink of human-level artificial intelligence – and it’s about to cause chaos
An AI agent called Manus has led to speculation that China is close to achieving artificial general intelligence, writes Anthony Cuthbertson. Experts warn that what comes next could be catastrophic ...