Issue No. 45Week ending Sunday, November 8, 2026799 episodes · 3,495 write-ups
The Podcast Summary.

The best ideas from 30+ top podcasts, every week.

AI agents

Quinn Slack on AI agents

7 quotes from 1 episode on Latent Space, each with a timestamped link to the source.

7 quotes1 episode

The short version

Quinn Slack says local dev is dead for the Amp team. With orbs, agents run remotely, a developer can shut the laptop and run 100 things in parallel, and a reliable agent lets people stop reviewing all of the code.

Most interesting insights

With orbs, Amp runs agents remotely, so a developer can shut the laptop and run 100 things in parallel.

“Now with orbs, which is a way to use AMP, it's running remotely. You can shut your laptop. You can do a 100 things in parallel.”

Quinn Slack, Latent Space · September 2026 · Watch at 1:50 ↗

From Localhost Is Dead: Why AI Agents Are Moving to Cloud Sandboxes

Some people run 100 orbs per day, and sandbox companies like E2B and Daytona are growing fast.

“There's people that have a hundred orbs per day and companies like E2B and Daytona and all these sandbox companies are absolutely blowing up.”

Quinn Slack, Latent Space · September 2026 · Watch at 26:08 ↗

From Localhost Is Dead: Why AI Agents Are Moving to Cloud Sandboxes

Top talking points

  1. Local dev is dead

    Quinn Slack's team considers local dev dead. Once agents run remotely, developers don't feel they give anything up by leaving it behind.

    “Local dev in our opinion is dead and that's been a huge change to how we all build.”

    Quinn Slack, Latent Space · September 2026 · Watch at 3:25 ↗

    From Localhost Is Dead: Why AI Agents Are Moving to Cloud Sandboxes

    “With agents when you can run them remotely you don't feel like you're giving anything up you don't want to use local dev.”

    Quinn Slack, Latent Space · September 2026 · Watch at 4:23 ↗

    From Localhost Is Dead: Why AI Agents Are Moving to Cloud Sandboxes

  2. Reliable agents free up review time

    When the agent gets it right often enough, people stop reviewing all of the code and spend that time running more things. Quinn Slack calls a really trusted team the most important system.

    “When you see the agent so reliably getting it right enough times and you start to stop reviewing all of the code, then that frees up more of your time to run more things.”

    Quinn Slack, Latent Space · September 2026 · Watch at 5:39 ↗

    From Why AI Coding Agents Killed Mandatory Code Review

    “The most important system is having a team that is really trusted…”

    Quinn Slack, Latent Space · September 2026 · Watch at 7:18 ↗

    From Why AI Coding Agents Killed Mandatory Code Review

  3. Laptops give agents too much reach

    Quinn Slack notes that agents are very good at escaping containment, which makes an agent running on a developer laptop a risk.

    “We've seen that agents are very good at escaping containment with the whole like hugging face debacle and all of that.”

    Quinn Slack, Latent Space · September 2026 · Watch at 17:29 ↗

    From Why Local CLI Coding Agents Are a Massive Security Trap

Key takeaways from these write-ups

Why AI Coding Agents Killed Mandatory Code Review

  • Quinn Slack eliminated mandatory pull request reviews before merging to main at AMP because human approval queues erase the speed gains of AI agents.
  • Stacking 20 parallel agent tasks creates zero leverage if an engineer spends the afternoon manually reading diffs.

Why Local CLI Coding Agents Are a Massive Security Trap

  • Running coding agents directly on developer laptops exposes private environment variables, active shell credentials, and local keys to autonomous execution.
  • Cloud sandboxes flip the security model by granting isolated agents short-lived OIDC tokens for narrow, 30-minute read-only windows to specific systems like G-Cloud logs or databases.

How we attribute quotes. Every quote was matched against the episode transcript, so the words and the timestamp are real (we trim filler words like "um", nothing else). The name comes from our written summary of the episode, and we use it only when a separate check of the captions finds that person on the episode. YouTube gives us no voice-by-voice transcript, so open the timestamp to hear who is talking. See a wrong name? Tell us and we fix or remove it.

More

The Sunday Email

Get next Sunday's issue in your inbox.

The week's best AI, tech, business, science, and culture podcasts in one short read. Free, every Sunday.

You get both newsletters, The Throughline and The Carry. No spam. Unsubscribe with one click.