News
A former OpenAI researcher published new research claiming that the company's AI models will go to great lengths to stay ...
In these experiments, Jones and his collaborators tested multiple AI models. The research found that “when prompted to adopt ...
OpenAI's GPT-4.1 upgrade is more than just hype. Here's how this model outperforms GPT-4o in software development, long-form ...
GPT-4 attempted a similar test and didn’t do well, it would have landed somewhere in the 10,000s. This time, the improvement ...
As OpenAI continues to evolve its model offerings, GPT-4.1 represents a step forward in democratizing advanced AI for enterprise environments ...
Dieselgate' scandal, new research suggests that AI language models such as GPT-4, Claude, and Gemini may change their ...
A new benchmark can test how much LLMs become sycophants, and found that GPT-4o was the most sycophantic of the models tested.
Apple has announced updates to the AI models that power its suite of Apple Intelligence features across iOS, macOS, and more.
I had to ask ChatGPT for some extra explanation of this one, it said: “This one’s for the British hearts. It’s peak Gen Z ...
The new benchmark, called Elephant, makes it easier to spot when AI models are being overly sycophantic—but there’s no current fix.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results