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

📰
Your AI Isn’t the Product. It’s the Least Reliable Employee on Your Team.
Building reliable AI systems requires more than just smart models, it requires a system to catch errors and improve overall performance
Medium · AI
 📰
Stop Your LLMs from Forgetting: How a 2016 String Algorithm Solves AI's Biggest Memory Loss Problem
Learn how a 2016 string algorithm can help prevent LLMs from forgetting, solving AI's biggest memory loss problem
Dev.to · Tanaike
 📰
NVIDIA NIM: Production-Grade LLM Inference from a Single Docker Container
Learn how to deploy NVIDIA NIM, a production-grade LLM inference system, from a single Docker container and understand its internal workings
Medium · AI
 📰
What Are the Best Practices for Writing ChatGPT Prompts?
Learn best practices for writing effective ChatGPT prompts to improve output quality
Medium · ChatGPT
Up next
5 Levels of AI Agents - From Simple LLM Calls to Multi-Agent Systems
Dave Ebbelaar (LLM Eng)
Watch →