Multimodal AI Articles

Page 1 of 1 (4 articles)

11/27/2025 • EN

Quoting Qwen3-VL Technical Report

Technical report on Qwen3-VL's video processing capabilities, achieving near-perfect accuracy in long-context needle-in-a-haystack evaluations.

computer vision Evaluation Long Context Multimodal AI Positional Encoding

Simon Willison

11/18/2025 • EN

Trying out Gemini 3 Pro with audio transcription and a new pelican benchmark

A hands-on review of Google's new Gemini 3 Pro AI model, covering its features, benchmarks, pricing, and testing its multimodal capabilities.

AI Benchmarks Audio Transcription Gemini 3 Pro Model Pricing Multimodal AI

Simon Willison

3/15/2025 • EN

Using RealTime AI – Part 1: Getting Started with the Fundamentals of Low-Latency AI Magic

An introduction to RealTime AI, exploring the fundamentals of low-latency AI using the OpenAI Realtime API for fluid, conversational applications.

Low Latency Multimodal AI Openai API Realtime AI Voice Assistant

Code with Dan

12/2/2023 • EN

Rough Experiments with Llamafile and LLaVA 1.5

A developer experiments with Llamafile and LLaVA 1.5 to extract structured data from comedy show posters, testing its accuracy and JSON output capabilities.

computer vision Image Recognition Llamafile Llava Multimodal AI

Michael Lynch

Multimodal AI Articles

Quoting Qwen3-VL Technical Report

Trying out Gemini 3 Pro with audio transcription and a new pelican benchmark

Using RealTime AI – Part 1: Getting Started with the Fundamentals of Low-Latency AI Magic

Rough Experiments with Llamafile and LLaVA 1.5

Select Language