The ChatGPT Report’s Post

Hey friends, to prevent ChatGPT from crawling your site, particularly if you have a lot of original editorial content on the site, remember to add this snippet User-agent: ChatGPT-User Disallow: / to your robots.txt file. https://lnkd.in/ethGHGBd

OpenAI just released their guide to effective Prompt Engineering, all of it backs up things generally known - longer and explicit prompts, starting with a specific persona have always been my go-to demonstration to those more skeptical of the output of chatGPT: https://lnkd.in/e-gqEZdD

OpenAI recently released a prompt engineering guide with 6 specific strategies to help you unlock ChatGPT’s potential

GPTs for customized tasks is like a App Store or market place.. killer move and future for OpenAI LLM models. Watch OpenAI DevDay

https://lnkd.in/dyvdyNFR OpenAI DevDay, Opening Keynote: 1. 2M devs, 92% of Fortune 500 companies, 100M weekly users—strong numbers for OpenAI, given it launched just a year ago. 🙃 2. Introduction of GPT-4 Turbo: smarter, more cost-effective, and capable of handling larger requests. 3. Launch of GPTs - tailored instances of ChatGPT, GPTs store, and revenue-sharing program for the top GPTs builders. 4. Assistant API that allows management of the conversation stage, leverages external data sources, and invokes custom functions to make things happen. Personally, I think the introduction of tailored GPTs along with a store and revenue share for builders might be the biggest move. This could make OpenAI's business highly defensible, similar to how Apple and Google became oligopolies thanks to their mobile OS and App Store.

OpenAI CEO, Sam Altman, presents GPT-4 Pro with a few short demos. "We are thrilled to introduce GPTs. GPTs are tailored versions of ChatGPT for a specific purpose. You can build a GPT, a customized version of ChatGPT for almost anything with instructions, expanded knowledge, and actions, and then you can publish it for others to use." at 20:55 in video. https://lnkd.in/dcGeKGqg

Uncover the secrets of OpenAI APIs in this quick guide! 🚀 From chat applications with Chat Completion to image magic with DAL-E, discover the right tools for your project. Learn when to use Lang Chain and Embeddings for precise answers, and how Whisper can transform your audio tasks. Elevate your projects today! 🎥 #GeeksofKolachi #TeamGoK #OpenAIGuide #TechSimplified #QuickTips #APIsDemystified

Afraid of ChatGPT leveraging your website content? You can stop OpenAI's crawler (GPTbot) from crawling your site via a quick addition to your robots.txt file, or select which parts you'd like it to have access to.

I don't think the challenge is of making a change in how we integrate an app with LLMs. I think, the key challenge is the capability of open-source LLMs, as they are still far from where OpenAI's GPT-4 is. When you switch your app from OpenAI model to any open source LLM, the quality of responses degrade drastically, and that normally breaks things in the app. I have been playing with #autogen framework from Microsoft and some opensource LLMs like #mistral7b, #Mistral8x7b models from Together AI and fine tuned #codellama model from Phind but none of them worked as expected. Even OpenAI #gpt4 didn't work as expected in my case. Anyway switching the URLs and keys is the least of the challenges I see. With that said, it doesn't mean that opensource models are of no use. They can still be used in many use-cases where response accuracy or format is not so critical for an app to work.