function calling
-
OpenAI’s Quiet Transformative Updates
Read Full Article: OpenAI’s Quiet Transformative Updates
OpenAI has introduced subtle yet significant updates to its models that enhance reasoning capabilities, batch processing, vision understanding, context window usage, and function calling reliability. These improvements, while not headline-grabbing, are transformative for developers building with large language models (LLMs), making AI products 2-3 times cheaper and more reliable. The enhanced reasoning allows for more efficient token usage, reducing costs and improving performance, while the improved batch API offers a 50% cost reduction for non-real-time tasks. Vision accuracy has increased to 94%, making document processing pipelines more accurate and cost-effective. These cumulative advancements are quietly reshaping the AI landscape by focusing on practical engineering improvements rather than flashy new model releases. Why this matters: These updates significantly lower costs and improve reliability for AI applications, making them more accessible and practical for real-world use.
-
Google’s FunctionGemma: AI for Edge Function Calling
Read Full Article: Google’s FunctionGemma: AI for Edge Function Calling
Google has introduced FunctionGemma, a specialized version of the Gemma 3 270M model, designed specifically for function calling and optimized for edge workloads. FunctionGemma retains the Gemma 3 architecture but focuses on translating natural language into executable API actions rather than general chat. It uses a structured conversation format with control tokens to manage tool definitions and function calls, ensuring reliable tool use in production. The model, trained on 6 trillion tokens, supports a 256K vocabulary optimized for JSON and multilingual text, enhancing token efficiency. FunctionGemma's primary deployment target is edge devices like phones and laptops, benefiting from its compact size and quantization support for low-latency, low-memory inference. Demonstrations such as Mobile Actions and Tiny Garden showcase its ability to perform complex tasks on-device without server calls, achieving up to 85% accuracy after fine-tuning. This development signifies a step forward in creating efficient, localized AI solutions that can operate independently of cloud infrastructure, crucial for privacy and real-time applications.