An opinionated guide to which AI to use to do stuff
TLDR Dev ● Covered by 5 sources
The article guides users on which AI systems to use for different tasks, explaining that agentic systems now let AI handle multi-hour work autonomously with computer access, going beyond simple chatbot conversations. Claude Opus and ChatGPT's GPT-5.6 Sol at "High" thinking levels are recommended for high-stakes work, while ChatGPT Work and Claude Cowork (with company-provided computers) or Codex and Claude Code (with personal computer access) enable the most powerful applications. The key difference is that desktop versions grant the AI access to your actual computer, enabling complex multi-file projects like the author's book fact-checking task that took 30 minutes and verified 195 references without errors, fundamentally changing AI from a chatbot interface to a delegated work team.
Why it matters
Users can choose between accessible chatbots for low-stakes inquiries or more sophisticated models for high-stakes issues, with tools like ChatGPT and Claude providing capabilities for both personal and professional use. People should carefully set permissions, understand limitations, and experiment with real tasks to learn how AI can effectively support their needs.
Also covered by
- TechCrunch AI — OpenAI’s new voice mode makes it to the ChatGPT desktop app
- The New Stack — OpenAI and Anthropic both speak at once with dueling voice updates
- TechCrunch AI — Anthropic updates Claude voice mode with more capable models
- The Verge — Claude’s voice mode is now available for Opus and Sonnet
