Daniel Shanklin’s Post

Lately, I've been experimenting a lot with LLMs, and I noticed an interesting trend in the adoption of OpenAI API compatibility. Google is the latest to add OpenAI API compatibility for its Gemini LLMs: https://lnkd.in/efRfND5G ❓ Wondering why? Why not just stick with their own solution? Fast and friction-free onboarding is becoming the key to adoption in the fast-paced race of large language models (LLMs). OpenAI’s API has quickly become the de facto standard for integrating LLMs, thanks to its simplicity, early market presence, and broad ecosystem. Almost anyone who’s experimented with LLMs has likely started with OpenAI’s API, which provides a seamless experience from setup to getting the first response back, setting a high bar for others in the industry. For any company looking to compete in the LLM space, making the switch to their integration as easy as possible is critical. This is why we’re seeing so many providers embracing OpenAI API compatibility: xAI, Perplexity, and others already offer compatibility, and Hugging Face can serve any model with an OpenAI-compatible endpoint. ❓ Why is this important? This compatibility lets developers use new models simply by changing the endpoint in their OpenAI client—no additional code changes are required. Even better, it means developers can leverage existing tools, plugins, and the broader OpenAI ecosystem they’re already comfortable with. This friction-free integration removes barriers to trying out new solutions, making it easier than ever for customers to explore new options without leaving behind the tools they rely on. 💡 How you can translate this to your business? A smooth customer experience and easy onboarding can be a game-changer for any business. Here are a few ideas that you can take from this observation: 1️⃣ Lower barriers to entry Make it as easy as possible for customers to try your product. If they can integrate or onboard quickly, they’re more likely to stick around. 2️⃣ Adopt familiar standards: Wherever possible, align your product with industry standards that your customers are already familiar with. This reduces the learning curve and builds instant trust. 3️⃣ Focus on flexibility and compatibility: Design your product to work seamlessly with other tools your customers might already be using. Flexibility empowers users to experiment with your solution without fear of reworking everything. A great user experience isn’t just a feature—it’s a strategy. When customers can test your product with minimal effort, you create a powerful first impression and open the door for broader adoption. #developerexperience #dx #ux #openai #gemini #llm #observation

Stack Overflow signed a deal with OpenAI, announced Monday. Two things to think about: 1. Contributors aren't getting compensated for the value of their contributions. I'm not making a moral or legal point, just a practical one. It kinda sucks creating other people's value for free when they flaunt it. At least with open source generally, you're sorta insulated from the monetization by anonymity of reuse. At the same time, any community that doesn't ban you is always going to be a cool hang if you're a halfway interesting contributor or person. 2. People worry about LLM generated content feeding the LLMs and making the LLMs regress. Don't worry about that. It won't happen. There is a different problem. LLM makers won't let their LLMs regress on metrics that matter (no matter how bullshitty the metrics). They will have to spend more time and money filtering their training data sets as they become less human and more generated. That actually sounds like an activity OpenAI can saddle SO with. "We'll pay you for ongoing use of your data so long as your data improves." The fun part is that it will take time and GPU money in "pre-training" to prove that iterations are improving. In short, LLMs won't regress. They will get more expensive. Qualified training data will cost more. This is a critical business insight in this space, and is probably very different than whatever narrative you've bought into. If you need this kind of insight across your business, I am available to help you, from consultant and projects to full time. Message me. H/T Axel C., who is really good at LinkedIn and will probably end up monetized without compensation if he isn't already. #WrittenByMe

For those using the #GoogleGemini Google have announced Gemini's integration with the #OpenAI Library . This integration allows developers to: 👉 Access Gemini models through OpenAI's familiar interface 👉 Use both Chat Completions API and Embeddings API 👉 Implement Gemini using the OpenAI library through Python, JavaScript/TypeScript, or REST API calls OpenAI's API is becoming the de facto standard for LLM interactions. This is similar to how Amazon S3's API became the de facto standard for object storage, with many services (including Google's own Cloud Storage) offering S3-compatible APIs. We're seeing a similar pattern emerge where: 👉 OpenAI's Chat Completions API structure has become a reference implementation 👉 Multiple LLM providers are adopting OpenAI-compatible endpoints: ➡️ Gemini (Google) ➡️ Ollama ➡️ Anthropic (through Claude compatibility) ➡️ Many open-source LLM platforms This standardization brings several benefits: 👉 Makes it easier to switch between different LLM providers 👉 Enables easier multi-model deployment strategies 👉 Simplifies the creation of abstraction layers and tools Google's decision to implement OpenAI compatibility for Gemini is particularly significant given their market position - it suggests they recognize the practical value of adopting this. #ai #enterpriseai https://lnkd.in/euZW4xsZ

Last week, I learned about fine-tuning while updating one of the tutorials. It's amazing that using tools from Cloudflare, one can build AI apps quickly! If you want to learn about fine-tuning, here's the tutorial: https://lnkd.in/dWe337cd

🚨 Why isn’t anybody talking about OpenAI’s Realtime API?! 🚨 There’s been no hype around it, but it’s truly transformative! I haven’t been this excited about a piece of tech since ChatGPT or when I first started using Midjourney. I recently built my own version of Samantha from the movie Her — which, by the way, is one of my favorite movies ever. 🎥 I still remember watching it in the cinema around 10 years ago. At that time, I was already studying AI (or machine learning as we called it then), and after finishing the movie, still covered in tears, I turned to my friend and said something like “This won’t happen in our lifetime, maybe in 50 years.” Fast forward to today, and I’m not just interacting with Samantha — I’m building her! With the Realtime API from OpenAI, I created a real-time, speech-to-speech agent, and it’s incredibly powerful. 🗣️💻 This agent uses "tools" — a combination of code, API calls, and LLM prompts — to perform specialized actions. Whether it’s writing or executing code, generating images, or even crafting LinkedIn posts, the sky’s the limit here! And it all happens blazingly fast, hugely reducing the latency between thought and action, all while having a completely natural conversation with Samantha. The best part? I built all of this over the weekend completely for FREE by taking advantage of the Microsoft Azure Free Trial and a couple of free APIs like Together AI's FLUX, Tavily, and Groq, and with 100% Python code — using Chainlit for the chatbot UI (huge shoutout to Willy Douhard for his amazing demo) 🚀 Below are the highlights of my first conversation with Samantha! If you’re as excited about this as I am, check out my two YouTube videos: • https://lnkd.in/dWKkrh_4 — I explain how the Realtime API works and how you can build your own Samantha for FREE • https://lnkd.in/dpfcx5tB — Watch the full uncut demo and see a breakdown of the code behind her 📌 Link to the GitHub repository in the videos. 💡 These are my very first YouTube videos, so I’d appreciate some love in the form of a share, like, and subscribe! 🙌 The future is here, and the possibilities are endless. What will you build with this? #OpenAI #RealtimeAPI #AI #GenAI #VoiceAgent #Chainlit #Python

DataStax Aims To Simplify Building AI Apps With RAGStack https://lnkd.in/gfTxqiYr ChatGPT wowed us all, but it was actually the simplest possible demonstration of what a large language model (LLM) could do, contended Ed Anuff, chief product officer at DataStax, a company that offers a distributed cloud database built on the open source Apache Cassandra. “It’s taking its previous response and the previous interactions that are called the history — it’s taking those and adding your new question as an additional prompt, and it’s bundling all that up into a context and shipping it to the LLM, and it keeps repeating that,” he said of ChatGPT. “When ChatGPT was first released, that’s simply all that it was doing. The results that we experienced were pretty cool, but from a computer science program standpoint, it was actually pretty simple.” Retrieval Augmented Generation (RAG) is one way to supplement an LLM’s knowledge. He compared RAG to notecards that help you stay focused and factual when speaking about a topic. RagStack: the idea is to offer a set of technologies, similar to what the LAMP stack did for web development, that can be used to create AI applications. “Let’s go and retrieve these, these very accurate sources of knowledge that are retrieved through traditional database lookups,” he said. “In some cases — in a lot of cases — [you] use vector database lookups to get at things and to feed those into the LLM, and then LLM just uses its language facility to craft that response.” RAG can work through different mechanisms, including simple methods such as search and more complex methods such as turning a question into database queries, he said. The results post-RAG are “grounded,” meaning the LLM results are more accurate because the LLM used specific, factual information supplied alongside a query rather than relying solely on its own training data, he explained. This approach enhances accuracy by avoiding speculative or incomplete answers, resulting in responses that are more aligned with the provided information and thus more reliable, he added. “All of those result in behind the scenes, a bunch of information being gathered that is then fed with your original question into the LLM,” he said. “What the LLM does is — rather than going and relying on its own knowledge that it was trained on — it uses that information that was supplied to it, and then the LLM responds.” Creating AI Apps With RAGStack Recently, DataStax updated its offering to make RAG application development 100 times faster, the company announced at RAG++ in San Francisco. To do this, it’s using what it calls the RAGStack. The idea is to offer a set of technologies, similar to what the LAMP stack did for web development, that can be used to create AI applications. To support its RagStack vision, the company also launched a hosted version of Langflow on the Astra Cloud Platform. Langflow is an open source visual framework for building RAG applications....

Good work by Amiruddin Nagri. Bodhi app is a great way to start learning about LLMs.

Don't listen to anyone who says you can't learn new things. I didn't know much about coding or LLMs when ChatGPT came out, but I did know I needed to learn more about LLMs and how they work to keep up with the latest developments. And yesterday, I managed to set up and run my own AI powered search engine (https://lnkd.in/gqqcRtmd) on my computer using Docker and Ollama running Llama3. This might not seem like a big deal for most, but for me it was the result of a lot of self learning and trial and error. Mostly error. It's never too late to learn something new and improve your skillset. Keep challenging yourself and you'll be surprised at what you can do!  #neverstoplearning #newskills #expandyourskillset #LLMs #Docker #Ollama #Llama3 #perplexica #ai #perplexity

🚀 Learn LLMs Hands-On: Free Workshop with OpenAI APIs and Bodhi App Hello AI Learners! Eager to understand what the buzz around Large Language Models is really about? Want to get your hands dirty building GenerativeAI/LLM-based apps? I'm launching a FREE LLM Workshop for tinkerers and learners like you. My goal is to have you start building LLM/GenerativeAI based apps by the end of the workshop. 𑁍 What is Bodhi App? Bodhi App allows you to run Open Source/Open Weights LLMs from Huggingface locally on your machine. Using Bodhi App you: - Do not have to pay for proprietary APIs - Have data privacy, as nothing leaves your system - Use OpenAI compatible APIs, making it easy to switch https://lnkd.in/gCPz8g6a 💸 Is it really FREE? Yes, it's 100% FREE! This workshop isn't a teaser for a paid follow-up. What we design and decide here is exactly what you'll get in the workshop. 🤔 What's the catch? This workshop is our way of building a community around Bodhi App. You get to learn about LLMs, and we get our first users - hopefully turned evangelists. Wouldn't you call that a win-win? 🤗 🧐 And why should I learn LLMs from you? Let me formally introduce myself. I'm Amir, the founder and developer of Bodhi App. I've been fortunate to have an amazing learning journey in technology. In my last stint, I spent 5 incredible years at Gojek/GoTo, the SuperApp of Southeast Asia. At Gojek, I started as Head of Engineering for Mobile, architecting the mobile app from the ground up to support our SuperApp vision. Later, I headed various teams including Data, DevOps, Systems, and Operations Tech in leadership roles. I've been exploring Generative AI for over 5 years. In the last 3 years, I've been focusing full-time on GenerativeAI ideas, working on enterprise semantic search prototypes, a co-pilot for Twitter, Stable Diffusion, and more. My Generative AI journey includes: - Presenting winning GenerativeAI prototypes to Aidan Gomez (founder of Cohere and author of the transformers paper) - https://bit.ly/4bHNk92 - https://bit.ly/3RZGhkW - https://bit.ly/4bwR6Sl - https://lnkd.in/guxWRqRa - Delivering a paid and packed, hands-on Stable Diffusion workshop (http://has.gy/PT8n) - Authoring a highly-rated, and free Stable Diffusion Udemy course - https://bit.ly/intro2sd I hope this gives you confidence in my credentials as a technologist, generative AI expert, and hands-on workshop designer/trainer. 🙂 🤗 Next Steps? Ready to join? Take the first step by filling out our quick survey! We're in the process of understanding where our learners are in their journey and what they'd like to learn. Your input will help us design the perfect workshop for you: https://bit.ly/4604oph ❤️ Support Us Excited about this opportunity? Help us spread the word! Like, repost, or drop a comment to help more curious minds discover this workshop. Know someone who'd benefit? Share it with them! Thanks. #AIWorkshop #LearningAI #OpenSource #BodhiApp

About AI hallucinations polluting Google ... "Despite the hallucinations, we regularly hear 'Even if imperfect, we prefer to have something 80 percent correct, [rather] than nothing at all'." This is a frustrating response, but ... it's true. I keep hearing this from developers. The really top-notch ones who use AI regularly say that the answers aren't great, but they're a great start. It's the inexperienced ones who flounder and that's a serious problem. They often don't know they're pushing bad code. Meanwhile, Google search, the primary driver behind their ads, and thus the primary driver behind their income, has been floundering for two years. I've already started using https://www.perplexity.ai/ for most of my searches. It's rumored that OpenAI is going to introduce a search competitor (perhaps within the week!). We're finally closing in on better techniques to reduce hallcinations to lower-than-human levels, but until they're vetted and widely deployed (and affordable), this mess is going to continue. #AI #AIAdoption #OpenAI #Gemini #Claude #LLMs https://lnkd.in/gZYEtsqg