OpenAI is winding down self-serve fine-tuning. Here are the models you can still fine-tune, the current API syntax, published pricing, and the decisions to make before the window closes.
Stephen M. Walker IIOpenAI is winding down its fine-tuning platform. Here is what remains fine-tunable in the GPT-4 family, the current API and data format, and the available alternatives.
Stephen M. Walker IIA repeatable workflow for mixed teams to decide whether a new prompt version is actually better, and to keep a written record of why.
Stephen M. Walker IIAn opinionated AI startup stack organized by the work each tool does, with overlap, security concerns, and clear reasons to skip each product.
Stephen M. Walker IIThis comprehensive guide provides developers, product managers, and AI Teams with a structured framework for optimizing large language model (LLM) applications to achieve reliable performance. It explores techniques like prompt engineering, retrieval-augmented generation, and fine-tuning to establish strong baselines, fill knowledge gaps, and boost consistency. The goal is to systematically evaluate and improve LLM apps to deliver delightful generative experiences.
Stephen M. Walker IIIn this article, we provide a comparative analysis between Google's Gemini Pro and OpenAI's GPT-3.5, evaluating their performance, scalability, and cost-effectiveness.
Stephen M. Walker IIWhat a year of conversations with AI teams building products in 2025 taught us about roles, team shapes, and evaluation.
Stephen M. Walker IIMaster the art and science of crafting prompts that precisely convey context and intent to transform how LLM systems interpret and respond to queries.
Stephen M. Walker IIIn this post, we dive into Retool's State of AI 2023 report, analyzing key findings from a survey of over 1,500 tech professionals. We explore current AI usage, tooling preferences, and future outlooks, providing insights into how generative AI tools are being leveraged today and the evolving expectations.
Stephen M. Walker IIThe Klu team evaluates the new functionality rolled out by OpenAI this week.
Stephen M. Walker IIAs Azure OpenAI continues gaining traction for its speed and startup credits, understanding the key differences from the public OpenAI API is key.
Stephen M. Walker IIIn 2023, Generative AI models like ChatGPT dominated headlines and sparked calls for regulation, while risks from physical AI systems like autonomous vehicles and deepfakes went largely overlooked.
Stephen M. Walker IIStartups need to work smart and efficient. This blog post explores the top AI tools we use daily that help streamline operations, create content, and automate tasks.
Stephen M. Walker IIBreak down common AI misconceptions around understanding, controlling, and aligning large language models, highlighting techniques like RLHF that shape model outputs to human preferences.
Stephen M. Walker IIBuild your first Klu Action with the Python SDK in 5 Steps
Stephen M. Walker IIBuild your first Klu Action with the TypeScript SDK in 5 Steps
Stephen M. Walker IIExpanding our global deployment of OpenAI GPT-4 across 12 regions, emphasizing redundancy, load scaling, and regional privacy compliance.
Stephen M. Walker IIOpenAI GPT-4 Model Card
Stephen M. Walker IILearn how to fine-tune OpenAI GPT-3.5 Turbo using your own data with steps for data preparation, training, evaluation, and deployment to create customized LLM deployments for your specific applications.
Stephen M. Walker II (Co-Founder / CEO)Discover the top 5 open-source large language models in 2023 that developers can leverage, including LLaMA, Vicuna, Falcon, MPT, and StableLM. Compare model details like architecture, data, metrics, customization, community support and more to determine the best fit for your NLP projects.
Stephen M. Walker II (Co-Founder / CEO)An analysis of the best AI products released in 2022-2023, their impact on the ecosystem, and what this means for the future.
Stephen M. Walker IIOpen source LLMs like Gemma 2, Llama 3.1, and Command R+ are bringing advanced AI capabilities into the public domain. This guide explores the best open source LLMs and variants for capabilities like chat, reasoning, and coding while outlining options to test models online or run them locally and in production.
Stephen M. Walker IIIn this article, we'll dive into the current state of frontier models, exploring their capabilities, limitations, and the gap between benchmarks and real-world performance. We'll introduce QUAKE, a new benchmark designed to evaluate LLMs on practical knowledge worker tasks, and share our findings on model performance across various domains.
Stephen M. Walker IIMultimodal AI Models are transforming the landscape of artificial intelligence by enabling systems to process and understand multiple data types simultaneously, much like human cognition. This blog post dives into the power and potential of these models, exploring notable examples like GPT-4-V, LLava 1.5, and Fuyu-8B. We will discuss the challenges and solutions in multimodal AI integration, and explore their real-life applications and future implications. Join us as we unravel the future of artificial intelligence through the lens of multimodal AI models.
Stephen M. Walker IILearn how to develop an AI vision, foster a supportive culture, build robust data pipelines, upgrade infrastructure, embed ethical AI safeguards, and track AI success through actionable strategies.
Stephen M. Walker II