Let’s expand our network and follow each other on social networks. If you have 𝕏, Linkedin or a Youtube channel. Post it in the comments and let’s connect. My accounts: 𝕏: www.x.com/Lyle_AI LinkedIn: https://www.linkedin.com/in/clintinlylekruger Just starting out with Youtube shorts too. Have a great day!

I have stumbled upon a site that is better than perplexity and Google in my personal opinion and I've been tinkering with it for about a week now. It does a great job of curating knowledge from various sources using AI search and the company recently raised a 17 million dollar series A. I'm planning to make a guide on using this site in the coming week. Today I want to share a tiny site that I've been using to create landing pages in 60 Seconds, I'll leave the tutorial in the workspace as a post later on. What are some interesting tools you are currently using?

A valued member posted a question on how to turn SKU data into Sales Quotas. This is not a bulletproof solution, but should help in the short-run as a solid workaround. 🧰 Who is this useful for: - Sales Managers - Business Analysts - E-commerce Owners - Data Specialists STEP 1: Getting Started To convert your Stock Keeping Units (SKUs) into a sales quote using GPT, start by preparing your data. You'll need a CSV file containing your sales information. This file should include details such as customer names, purchase dates, SKUs, sizes, rates, and gross amounts. STEP 2: Import Your Data Open a new ChatGPT tab and import your CSV file. Paste the data into the chat. The GPT model will list out the data, showing all the details like customers, purchase dates, product details, and prices. STEP 3: Filter and Categorize Your Data The GPT will analyze the data and categorize it. It will ask for customer information to create a specific sales quote. For example, if you want to create a quote for a customer named Razia, input her name when prompted. STEP 4: Generate the Sales Quote The GPT will generate a sales quote for the specified customer. The quote will include: - Unit numbers and indices - Purchase dates - Product details (SKUs, sizes, rates) - Pricing in table format - Total amount owed by the customer If you have additional details like the customer’s address, you can add them to the quote. The GPT will also allow you to include terms and conditions, as well as signature fields. STEP 5: Verify and Customize Always double-check the generated quote for accuracy. LLMs can sometimes make errors, so verification is crucial. You can also customize the quote by adding any additional conditions or notes specific to your business needs. Hope you enjoyed this mini-tutorial. Have a great weekend!

We all hear about benchmarks these days And that LLMs are measured against them But what exactly are these benchmarks? Here's an explainer: (🔖Bookmark for later) 1. HumanEval and MultiPL-E HumanEval and MultiPL-E are benchmarks used to evaluate the performance of AI models in generating and understanding code. These benchmarks are designed to assess how well a model can complete programming tasks, understand code syntax, and generate accurate code solutions. HumanEval: Purpose: Measures the ability of AI models to generate correct code solutions for given programming problems. Tasks: Typically involves coding challenges where the model must write functional code snippets based on a problem description. Performance Indicator: Higher scores indicate better understanding and generation of code, reflecting the model’s capability in code-related tasks. MultiPL-E: Purpose: Evaluates the model's performance across multiple programming languages. Tasks: Similar to HumanEval but expanded to include various programming languages, testing the model's versatility and multilingual coding proficiency. Performance Indicator: Outperforming Llama 3.1 405B instruct and scoring just below GPT-4o suggests that Mistral Large 2 is highly proficient in coding tasks and can handle multiple languages effectively. 2. MATH (0-shot, without CoT) MATH (0-shot, without CoT) is a benchmark designed to assess the mathematical reasoning and problem-solving abilities of AI models without prior contextual examples (0-shot) and without chain-of-thought (CoT) prompting. Purpose: Tests the model's inherent ability to solve mathematical problems without additional hints or step-by-step guidance. Tasks: Includes a variety of math problems ranging from basic arithmetic to more complex mathematical reasoning. Performance Indicator: Falling only behind GPT-4o indicates that Mistral Large 2 has strong mathematical reasoning abilities, capable of solving problems independently without guided thinking processes.

Would love to get your take on these platforms. It seems like a great blend on ChatGPT/Claude and Zapier.