For those who haven't tried it yet it's a new feature in GPT-4o that lets the chatbot proactively message you at scheduled times. Just type something like "Remind me to check my email tomorrow at 10 am," and it will set the reminder for you automatically. When the time comes, you'll get a push notification or an email with the message.

Examples I've successfully tested:

Prompt engineering has changed a lot recently. I remember around this time last year, strict prompt engineering rules were a must. From You are a professional persona setting, to zero-shot, few-shot CoT techniques, these were necessary for quality outputs

Nowadays, it feels as if AI models do the engineering all by themselves without user input. They understand us well even if we re just casually typing (some call it lazy prompting , and I even saw a product related to this on PH)

Okay, so I know everyone's feed has been taken over by the Studio Ghibli but I'm curious what else people have been able to create or seen that's really left an impression. Here are some that I've created! Also on X.

Hello everyone !

I recently posted in this forum about creating the easiest tool to launch AI models locally and if you're interested ?

OpenAI has released a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer followup questions, admit its mistakes, challenge incorrect premises, and reject inappropriate requests.

Hi everyone,

I'm currently exploring a project idea : create an ultra-simple tool for launching open source LLM models locally, without the hassle, and I'd like to get your feedback.

The current problem:

I'm not a dev or into IT or anything, but I've become fascinated by the subject of local LLMs , but running an LLM model on your own PC can be a real pain in the ass :

Earlier today I shared how you can use it to swap your face into any existing thumbnail.
But I've been testing changing the emotion in my face and adding things like pointing fingers!
Thumbnails are one of the most important things to help your channel grow. Get the clicks!
ChatGPT just made it insanely easy for anyone to create high quality thumbnails!

https://www.facebook.com/photo/?...

ChatGPT can now search the web in a much better way than before. You can get fast, timely answers with links to relevant web sources, which you would have previously needed to go to a search engine for.

Powered by a version of OpenAI o3 optimized for web browsing and python analysis, deep research uses reasoning to intelligently and extensively browse text, images, and PDFs across the internet.

I have been playing around with some GPT-4 plugins recently (like the travel ones that book flights for you), and it got me thinking: Could this plugin ecosystem eventually replace the traditional app store model (like on iOS or Google Play)?

Right now, we switch between dozens of apps for random tasks (booking a hotel, checking the weather, ordering groceries), but if ChatGPT can handle all that directly, why would we need separate apps for each thing? It almost feels like a central AI OS.

• Is that too futuristic of a prediction, or do you think it might be coming sooner than we think?

• How do you see this impacting smaller developers does it open up new opportunities or create more competition under one AI umbrella?