| I was working on debugging one of our feature which is AI battle. I just make this for fun and more to have a quick compare of different ai models answers. So shortly Ive asked 2 different ai models to rate from 1-5 the best ai models. Guess what, the models is always gives better scores for themselves. Gpt said its 5/5 🥹, but other said different results. Are its trained to said that its better? [link] [comments] |