OpenAI has unveiled yet another artificial intelligence model. This one is called o1, and the company claims it can perform complex reasoning tasks more effectively than its predecessors. Apparently, o1 was trained to “spend more time thinking through problems before they respond.” According to the company: “[the models] learn to refine their thinking process, try different strategies and recognize their mistakes.”
That more considered response means it’s significantly slower at processing prompts than GPT-4o. And while it might be thinking more, o1 hasn’t solved the problem of hallucinations — a term for AI models making up information. OpenAI’s chief research officer Bob McGrew told The
→ Continue reading at Engadget
