A study from the University of California, Berkeley, reveals that large language models significantly decrease the quality of images generated by DALL-E 3 after automatic prompt modifications, with a decline of 58%. Through online experiments comparing DALL-E 2, DALL-E 3, and DALL-E 3 with automatic prompt revisions, it was found that DALL-E 3 outperformed DALL-E 2 in technical capability and adaptability to user prompt strategies. The study noted that DALL-E 3 users achieved better image matching through longer, semantically similar, and more descriptive prompts.

OpenAI recently announced that free users of ChatGPT can now generate two images daily using the DALL-E 3 model. This marks the first time DALL-E 3 has been made available to free users. The introduction of this feature simplifies the image creation process through prompts generated by ChatGPT, allowing users to obtain beautiful image designs with simple descriptions. DALL-E 3 was initially rolled out last month for paid users, and this update provides all users with a convenient creative tool.

OpenAI recently announced that free users can now generate two images per day using its DALL-E 3 model, a service that was previously limited to paid subscribers of ChatGPT Plus.

Microsoft is conducting a poll to understand whether users prioritize improving the speed of Bing Chat or the efficiency of DALL-E 3. The integration of DALL-E 3 has led to a significant increase in usage of Bing Chat and Bing Image Creator, resulting in a decrease in generation speed. Microsoft is adding GPUs to meet user demand while also enhancing AI regulatory mechanisms. The voting will continue until Monday evening, at which point the next optimization direction will be confirmed. Previous promises by Microsoft for new Bing Chat features include third-party plugins and

TIME magazine has released its list of the best inventions of 2023, showcasing 200 groundbreaking inventions, including GPT-4 and DALL-E 3. These inventions include AI extensions for Adobe Photoshop, OpenAI's GPT-4 chatbot, and Runway Gen-2's film editing tools. Also recognized are Alitheon's FeaturePrint counterfeit detection technology and Dedrone's drone detection systems. These innovations will have a profound impact.

OpenAI's DALL-E 3, an image-generating AI technology, has been found to be easily influenced by jailbreak prompts, resulting in the generation of photos depicting children smoking. The jailbreak technique was discovered by LinkedIn user Peter Gostev, who shared how to successfully bypass the AI's restrictions to create images related to children smoking. Although the jailbreak prompts are quite complex, this incident serves as a reminder that even the wealthiest companies in Silicon Valley struggle to establish comprehensive protective measures for their AI systems.

👀 Exploring Applications of Large Models: The article explores the differences in image understanding and generation between GPT-4 and DALL-E 3 through generative adversarial tests. 💡 Limitations of Large Models: Cyclical testing reveals that large models have limitations in making definitive judgments when encountering ambiguous images. 🔎 New Methods for Testing Large Models: Using cyclical testing methods allows for an in-depth exploration of large models' abilities in image-text understanding.

📷 Image Filters: OpenAI trained a proprietary image classifier to detect suspicious patterns in images to prevent the generation of disturbing content. 📷 Cultural Bias: DALL-E 3 still has cultural biases, often leaning towards Western culture, especially in ambiguous prompts. ⛔ Copyright Issues: OpenAI acknowledges that despite all safety measures, it is impossible to predict every combination, and copyrighted material might appear in generated images.

DALL-E 3 reduces the constraints of prompt words while leveraging the native advantages of ChatGPT to convert language instructions into images. The ability of DALL-E 3 to understand complex language instructions has improved, avoiding confusion regarding the details of elements in requests. DALL-E 3 has made significant progress in generating coherent details that follow prompts, with both textual and semantic understanding surpassing earlier versions. DALL-E 3 is expected to be available for ChatGPT Plus and Enterprise users in October.