Skip to content
PodSubs
ShowsPeopleGuestsJobsNewsEvents
More
BlogPodCred
Menu
ShowsPeopleGuestsJobsNewsEventsBlogPodCredNetworksSign in
Join nowSign in
  • Shows
  • People
  • Jobs
  • News
  • More
    • Guests
    • Events
    • Blog
    • PodCred
    • Networks
    Join nowSign in

Fragmented - AI Developer Podcast

Fragmented - AI Developer Podcast artwork

310 - Mitchell Hashimoto on Ghostty & His Agentic Coding Workflow

Apr 14, 20261 hrAudio

Mitchell Hashimoto co-founded HashiCorp, built some of the most impressive DevOps tools like Vagrant and Terraform, sold the company to IBM - and then built a terminal. Ghostty is now where a huge chunk of agentic coding actually happens. Mitchell was an AI skeptic. We walk through his six-step adoption framework and the workflows he uses day to day - warm-start research, Hail Mary prompts across twenty GitHub issues, and knowing when to let the agent slam dunk it. Full shownotes at fragmentedpodcast.com. Show Notes HashiCorp Vagrant Terraform IBM acquires Hashicorp Ghostty Ghostty - Mitchell's fast, native terminal built for platform integration across Mac and Linux Terminal shell SSH - secure shell PTY - pseudoterminals Terminal Multiplexers tmux - most popular open source one XTGETTCAP by xterm libghostty - the cross-platform terminal emulation library that powers Ghostty's core xterm-js - powers terminal for apps like VSCode and the cloud Jedi Term - Intellij's embedded terminal Ghostty is now a non-profit cmux - native macOS terminal multiplexer built on libghostty - a fork Mitchell champions Free Software Definition - the 4 essential freedoms The freedom to run the program as you wish, for any purpose. The freedom to study how the program works, and change it to make it do what you wish. The freedom to redistribute copies so you can help others. The freedom to distribute copies of your modified versions to others. Mitchell's tweet on unsolicited PRs and transfer of ownership The AI Adoption Journey My AI Adoption Journey - Mitchell's blog post outlining his five-step framework Step 1: Drop the Chatbot Episode 301 - AI Coding ladder - Different stages of AI adoption Step 2: Reproduce Your Own Work Step 3: End-of-Day Agents OpenAI Deep Research - kick off research tasks for a "warm start" the next morning Spine AI research - deep research tool for longer, hour-long analysis tasks Step 4: Outsource the Slam Dunks Claude status hooks - warcraft peons Conductor Step 5: Engineer the Harness Episode 307 - Harness Engineering - Fragmented's deep dive on harness engineering, heavily inspired by Mitchell's post Step 6: Always have an Agent running Peter Steinberger Codex plugin for Claude Code Get in touch We'd love to hear from you. Email is the best way to reach us or you can check our contact page for other ways. We want to hear all the feedback: what's working, what's not, topics you'd like to hear more on. Contact us Newsletter Youtube Website Co-hosts: Kaushik Gopal Iury Souza [!fyi] We transitioned from Android development to AI starting with Ep. #300. Listen to that episode for the full story behind our new direction.

Audio and video play straight from the show's own hosting. PodSubs stores and serves no media.

Hosts and Guests

Nobody is credited on this episode yet.

Credit the people on this episode

Be the first to rate this episode

More episodes

All episodes
  1. 312 - Understanding Pi Durable with Mario & Armin of Earendil

    Oct 20, 20261 hr 1 minAudio

    What does it take to keep an agent working after its process dies? Pi creator Mario Zechner and Earendil co-founder Armin Ronacher join KG to explain Pi Durable: explicit tasks, crash recovery, and the primitives for...

    Credit the people on this episode

  2. 311 - Self learning harnesses are here

    Sep 6, 202613 minAudio

    Claude Code and Codex have been the mainstay agent harnesses, with OpenCode and Pi as the popular open-source alternatives. But two new entries are pushing what a harness even is: DeepSeek's Cordis kernel, where...

    Credit the people on this episode

  3. 309 - Background Agents

    Apr 1, 202626 minAudio

    Andrej Karpathy says the goal is to maximize how long an agent runs without your intervention. But there's a false summit most teams hit first: individual speed goes up while system speed stalls, your laptop roars under...

    Credit the people on this episode

  4. 308 - How Image Diffusion Models Work - the 20 minute explainer

    Mar 24, 202625 minAudio

    You already know how LLMs work from our popular 20-minute explainer. Now we take it to images. What does Michelangelo have to do with stable diffusion? More than you'd think. Walk away knowing how image generation...

    Credit the people on this episode

  5. 307 - Harness Engineering - the hard part of AI coding

    Mar 17, 202630 minAudio

    The hard part of AI coding isn't generating code - it's controlling quality, safety, and drift. Kaushik and Iury break down harness engineering: the five pillars for shaping an agent's environment and what it looks like...

    Credit the people on this episode