In testing, CriticGPT improved code review results by 60% compared to “traditional methods.” This model will be integrated into OpenAI Reinforcement Learning from Human Feedback (RLHF), which provides tools to evaluate complex AI performance, the company writes. Teams that used CriticGPT in experiments produced more comprehensive critiques and encountered fewer false flags of error.
Developers say CriticGPT is excellent at detecting errors in short answers, but needs further development for longer and more complex tasks.
Source: Ferra
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
