Stenobird

Episode

The Wirecutter Show: Tips for Using A.I. Smartly With Kevin Roose

Podcast
Hard Fork
Published
Dec 30, 2025
Duration seconds
2095
Processing state
processed
Canonical source
https://www.nytimes.com/column/hard-fork
Audio
https://dts.podtrac.com/redirect.mp3/pdst.fm/e/pfx.vpixl.com/6qj4J/pscrb.fm/rss/p/nyt.simplecastaudio.com/3e43d072-f8a5-430f-bc8e-4c70aafdf3c7/episodes/600f70f2-c565-48a7-b87b-f08fd674589d/audio/128/default.mp3?aid=rss_feed&awCollectionId=3e43d072-f8a5-430f-bc8e-4c70aafdf3c7&awEpisodeId=600f70f2-c565-48a7-b87b-f08fd674589d&feed=l2i9YnTd
JSON
/v1/public/podcasts/hard-fork/episodes/the-wirecutter-show-tips-for-using-a-i-smartly-with-kevin-roose
Markdown
/podcast/hard-fork/the-wirecutter-show-tips-for-using-a-i-smartly-with-kevin-roose.md

Actions

  • POST https://stenobird.com/v1/public/podcasts/hard-fork/episodes/the-wirecutter-show-tips-for-using-a-i-smartly-with-kevin-roose/transcription-requests
    Idempotently request low-priority transcript generation for this episode.
  • GET https://stenobird.com/podcast/hard-fork/the-wirecutter-show-tips-for-using-a-i-smartly-with-kevin-roose.md
    Read the agent-friendly Markdown representation of this episode resource.

Summary

Kevin Roose shares his practical framework for integrating various AI models into a daily workflow. The discussion focuses on matching specific LLMs to distinct tasks like coding, research, and creative writing.

Topics

  • Large Language Models
  • Artificial Intelligence
  • Claude
  • Google Gemini
  • Perplexity AI
  • NotebookLM
  • Productivity Tools
  • Automation

Highlights

  • Main idea: Different large language models excel at different specialized tasks
  • Practical takeaway: Use Claude for creative work and tasks requiring high emotional intelligence
  • Practical takeaway: Leverage Google Gemini for processing large chunks of text and deep research
  • Practical takeaway: Utilize NotebookLM to synthesize and chat with large collections of personal documents
  • Failure mode: Relying on a single model for all tasks can lead to inefficiency and wasted subscription costs

Chapters

  1. 1:00 The Case for AI Reviews: Kevin discusses the need for expert testing of AI tools, similar to how Wirecutter reviews physical products.
  2. 4:15 The LLM Landscape: An exploration of the difficulty in choosing between various paid language models without expert guidance.
  3. 10:15 Personal AI Workflows: Kevin details how he uses specific tools to summarize email inboxes and manage personal information.
  4. 13:05 AI for Writing and Translation: A look at the most common use cases for AI, including academic writing and language translation.
  5. 16:10 The Evolution of Chatbot Personality: How AI companies are moving toward more personable and human-like conversational interfaces.
  6. 22:05 Voice Dictation and Audio-to-Text: The utility of using AI models to transform speech into structured text for daily productivity.
  7. 25:10 Custom Instructions: How to use custom settings to eliminate preamble and force models to be direct and concise.