GPT-4o’s vision capabilities allow you to send images alongside text prompts and receive detailed, contextually aware responses about what the model sees. Released as part of GPT-4o in mid-2024, the vision API accepts standard image formats, handles multiple images per request, and produces responses that range from simple descriptions to complex reasoning about visual content. … Read more
Building a voice assistant with local LLMs means combining three components: a speech-to-text model that transcribes your voice, a language model that understands and responds, and a text-to-speech model that speaks the response aloud. None of these need to touch external servers — Whisper handles transcription locally, Ollama runs the LLM, and tools like Piper … Read more
Transcribing and analysing video with AI combines two capabilities — speech-to-text for the audio track and vision or language understanding for the content — to produce searchable transcripts, summaries, topic extractions, and structured insights from video at scale. The tooling for this has matured significantly: Whisper handles transcription reliably, and frontier LLMs handle analysis of … Read more
An image question-answering pipeline lets you send an image and a natural language question to a vision-capable LLM and receive a structured, actionable answer. The use cases range from product quality control and document processing to accessibility tooling and visual search. Building one well requires thinking through model selection, prompt design, how to handle batches … Read more
Writing tests with an AI assistant removes most of the friction that causes developers to skip or defer testing. Tests are repetitive, edge-case enumeration is tedious, and the boilerplate for mocks and fixtures looks nearly identical across hundreds of test files. AI handles all of this well. The challenge is knowing how to direct it … Read more
Building a full application with an AI coding assistant is a different experience from using AI for isolated tasks. The challenge is not getting the AI to write code — it will do that readily — but keeping the architecture coherent, the codebase understandable, and the quality high across a multi-session project that grows in … Read more
GitHub Copilot Workspace is GitHub’s answer to the agentic coding tools pioneered by Cursor and Windsurf — a feature that lets you describe a task in natural language and have Copilot plan, implement, and iterate on code changes across an entire repository. What distinguishes it from standalone AI IDEs is where it lives: directly inside … Read more
Cursor supports local models through Ollama, letting you run AI-assisted coding entirely on your own hardware — no API keys, no usage costs, no data leaving your machine. The quality is lower than frontier cloud models, but for privacy-sensitive codebases, offline work, or developers who run many short coding sessions throughout the day, local models … Read more
Cursor Composer is the agentic multi-file editing mode inside Cursor that transforms a simple code request into a sustained, multi-step coding session. Where a regular Cursor chat generates code for you to paste in, Composer reads your files, makes edits directly across multiple files, runs terminal commands, observes the output, and iterates — all within … Read more
Running Aider with a local LLM means you get AI-assisted coding with no API costs, no data leaving your machine, and no dependence on third-party services. The tradeoff is quality — local models are not yet as capable as frontier cloud models for complex coding tasks. But for the right use cases, the combination of … Read more
