The Future in Tech-Powered by LinkedIn Learning’s Post

Planning an LLM101 beginner workshop for #FOSSMeet. Will cover OpenAI basics, demo LLM potentials, teach open source LLM like Mistral7b/Gemma and to provide hands-on building time by giving free OpenAI credits. Any suggestions on topics to cover for my 6 hour workshop?

5 Rarely Used OpenAir Features You Will Benefit From | Top Step

If you've visited the OpenAQ Explorer (explore.openaq.org) recently, you may have noticed a ✨ new ✨ look AND a new feature - LISTS! Learn more about how you can build your own📝 Lists and navigate this new additional feature in the Explorer! 🌏 Register for our training on #OpenDataDay here: https://lnkd.in/gkqHt82e

Have you ever tried to work with over 50 billion #airquality measurements? I'll save you some time and just tell you right now it exceeds Excel's row limits, sorry. Working with this data from over 60,000 monitors can be hard, and the truth is, not everyone cares equally about all the data equally. Like children, I of course love each data point equally though. OpenAQ Inc just launched a new feature to let community-based organizations (or anyone else) focus on just the locations they care about to drive the most local impact. If you're using this feature, let them know! They are also running a training session with Asia, Africa, and Europe friendly timing to help explain how to work with the updated platform.

The OpenAI Assistants API now supports vision. You can create messages with image URLs or uploaded files, and your assistant will use the visuals as part of its context for the conversation.

Another moment of OpenAI being O̶p̶e̶n̶A̶I̶ ClosedAI. A lot has been happening since the model o1 came out. Many are trying to understand the ability behind such a model's superb performance by tricking o1 into revealing its thinking process. Most likely they have Reflection baked in with some complex CoT, which iteratively improves the response of the LLM. Although this is great for OpenAI as they are the first to achieve this level of success, thankfully these simple techniques are also being replicated by other open-source competitors too. Such simple techniques should be openly shared with the public instead, OpenAI has started sending Violation notices to the developers who are trying to reveal the "special prompts".

Context is still your biggest challenge in RAG - getting the right information from your documents to the LLM so it can answer questions. OpenAI just released is prompt guidelines for its new o1 models: “Limit additional context in retrieval-augmented generation (RAG): When providing additional context or documents, include only the most relevant information to prevent the model from overcomplicating its response.” from https://lnkd.in/eDDW8wan Despite repeated claims to the contrary, “context stuffing” still doesn’t work. You still need a product like Pinecone and an engineer who can optimize your LLM’s performance.

Learning Prompt Engineering has been a bit of trial and error. Here’s a neat guide from OpenAI to supercharge your prompts

OpenAI published a guide to make better prompts and get better results. Six strategies for getting better results: - Write clear instructions - Provide reference text - Split complex tasks into simpler subtasks - Give the model time to "think" - Use external tools - Test changes systematically https://lnkd.in/d-EuZ7BN #promptengineering #openai #artificialintelligence

Did you know that OpenAI has released guides on how to create top-notch prompts? https://lnkd.in/ehjFbsgv Less effective ❌: Summarize the text below as a bullet point list of the most important points. {text input here} Better ✅: Summarize the text below as a bullet point list of the most important points. Text: """ {text input here} """