← Back to KHAO

Business ·

ChatGPT’s new Images 2.0 model is surprisingly good at generating text

2 min read

Compiled by KHAO Editorial — aggregated from 1 outlet. See llms.txt for citation guidance.

◌ Single Source

Image accompanies the article at TechCrunch AI. No description was extracted from the source.

It used to be easy enough to distinguish between human-made and AI-generated imagery — two years ago, you couldn’t use image models to create a menu for a Mexican restaurant without inventing new culinary delights like “enchuita,” “churiros,” “burrto,” and “margartas.”

Key facts

Summary

It used to be easy enough to distinguish between human-made and AI-generated imagery — two years ago, you couldn’t use image models to create a menu for a Mexican restaurant without inventing new culinary delights like “enchuita,” “churiros,” “burrto,” and “margartas.” Now, when the reporter ask the brand new ChatGPT Images 2.0 model for a menu of Mexican food, it creates something that could immediately be used in a restaurant without customers noticing that something’s off. (However, ceviche priced at $13.50 might make me question the quality of the fish.) For comparison, here’s the result the reporter got from DALL-E 3 two years ago (at the time, ChatGPT did not generate images):. AI image generators have historically struggled to spell because they generally used diffusion models, which work by reconstructing. “The diffusion models are reconstructing a given input,” Asmelash Teka Hadgu, founder and CEO of Lesan AI, told TechCrunch in 2024.

Read full article at TechCrunch AI →