Nanome’s Post

OpenAI o1-preview A new series of reasoning models for solving hard problems. OpenAI o1-mini The o1 series excels at accurately generating and debugging complex code. To offer a more efficient solution for developers, we’re also releasing OpenAI o1-mini, a faster, cheaper reasoning model that is particularly effective at coding. As a smaller model, o1-mini is 80% cheaper than o1-preview, making it a powerful, cost-effective model for applications that require reasoning but not broad world knowledge. Read more:

Nice guide Logan Kilpatrick! I would also add the use of “roles”, not just personas. For instance, “You are a teacher responsible for helping a student learn about X. As a teacher, you are trained to help students figure things out on their own rather than giving them the answer directly.” In practice, this is like instilling “values” in the model that can dramatically improve its ability to target specific functional requirements for a given interface. I would also emphasize the use of ChatGPT (GPT4) as a means for fine-tuning prompts fed to smaller and less capable models. Give it a few good examples of ideal input/output and ask it to explain its reasoning, then use that as part of your CoT reasoning exemplars. I use this strategy all the time and it makes prompt engineering a breeze!

A guide to Prompt Engineering was recently published by OpenAI. It covers six strategies for getting better outputs from GPT models. 1. write clear instructions  2. Provide reference text 3. Split complex tasks into simpler subtasks  4. Give the model time to "think" 5. Use external tools 6. Test changes systematically

Do you want to have your own Fine-tunned OpenAI LLM model ? Now you have chance to train your own model from foundational LLM model for free until September 23rd. Take a look at OpenAI documentation to get insights how it could done. What are the benefits? 🔍𝐄𝐧𝐡𝐚𝐧𝐜𝐞𝐝 𝐏𝐞𝐫𝐟𝐨𝐫𝐦𝐚𝐧𝐜𝐞: Fine-tuning allows you to tailor GPT-4o mini to your specific needs, ensuring more accurate and relevant outputs for your applications. 💡 𝐂𝐨𝐬𝐭-𝐄𝐟𝐟𝐢𝐜𝐢𝐞𝐧𝐜𝐲: Compared to GPT-3.5 Turbo, GPT-4o mini is more cost-efficient, offering longer context and lower latency. This means you can do more with less. 🌐 𝐀𝐜𝐜𝐞𝐬𝐬𝐢𝐛𝐢𝐥𝐢𝐭𝐲: Currently available for Tier 4 and 5 users, OpenAI plans to extend this offer to all tiers gradually. Each organization gets 2M training tokens per day for free, providing ample resources to experiment and perfect your models.

Check out this insightful guide from OpenAI on optimizing results with large language models. It offers valuable strategies and tactics to enhance your prompt engineering skills. https://lnkd.in/eKHVvYbY

Working on implementing the OpenAI Assistant API. Bit wild but Vercel made a neat wrapper. Currently functional but times out on some runs or the run gets stuck in a pending state. Still digging 🤔 https://lnkd.in/eQXxugeN

Level up your LLM Ai game! Six tips directly from OpenAi on prompt engineering to unlock the best results : - Be crystal clear! ✨ The more detailed, the better! - They need context: Feed docs & pdfs... - Break it down, step-by-step. let the the LLM conquer small tasks - Patience is a virtue! Give me the model time to think,  Ask for a "chain of thought" - Compensate for the weaknesses of the model by feeding it the outputs of other tools...use RAG for instance - this one not a tip..but I had to include since OpenAi did..."Experiment & tweak! Test different approaches." yeah..no joke. #promptengineering #openai link to source : https://lnkd.in/g74KfJXz

New OpenAI model "gpt-4o-min" is out https://lnkd.in/g_MzPUJS. Smarter, faster and cheaper alternative to GPT-3.5-turbo. Also, multi-modal (vision + text). I love those releases. You get a better product, that is cheaper and faster! I am validating the model against my use-cases, so can't say anything about the performance myself, official data can be found by the link above.

Check out this AI Prompt Engineering Guide which comes directly from OpenAI. I learned several new tips!

New OpenAI model - gpt-4o-audio-preview (gpt-4o-audio-preview-2024-10-01), 128 000 tokens context window, 16 384 max. output tokens and knowledge cut-off Oct 2023 (https://lnkd.in/dCB3pvs3)