This Actually Surprised Me

Matt Wolfe · Intermediate ·🧠 Large Language Models ·2mo ago

Key Takeaways

Demonstrates ChatGPT's new image model capabilities

Original Description

ChatGPT’s new image model did something that blew me away 🤯 Usually, you'd have to download images from the source and drop them into ChatGPT with your prompt so the AI can use them in the output. But this new model was able to just grab them from the site using only the URL. Making flyers, ads, menus, promos, product images, etc. just got A LOT easier, and with a lot less worry that the AI is going to grab random hallucinated images or details from all over the place. Have you tried ChatGPT Images 2.0 yet? And did it impress you, or not so much? #ai #ainews #chatgpt #openai #genai
Watch on YouTube ↗ (saves to browser)
Sign in to unlock AI tutor explanation · ⚡30

Related Reads

📰
26 AI Models Compared: A 2026 Cost Guide (GPT-4o vs Claude vs DeepSeek vs Local)
Compare 26 AI models including GPT-4o, Claude, and DeepSeek to determine the best fit for your 2026 AI project based on cost and performance
Dev.to AI
 📰
I tested ChatGPT's Live Voice upgrade, and it almost felt human - how to try it
Discover how to try ChatGPT's Live Voice upgrade and experience human-like conversations
ZDNet
 📰
Building AI Data Pipelines — How to Feed Your LLM Fresh Web Data
Learn to build automated AI data pipelines to feed your LLM fresh web data, saving development time and reducing maintenance headaches
Dev.to AI
 📰
Changes to LLM pricing: Inceptron, Mara and Novita
Learn about the recent price changes for LLM models Inceptron, Mara, and Novita and how they impact your projects
Dev.to AI
Up next
5 Levels of AI Agents - From Simple LLM Calls to Multi-Agent Systems
Dave Ebbelaar (LLM Eng)
Watch →