<!-- mobian-agent-page publisher="dailydev" canonical="https://daily.dev/posts/orbin-with-amp-changelog-interviews-691--t8ggtafoz" -->

---
title: Orbin' with Amp (Changelog Interviews #691) | daily.dev
description: Quinn Slack returns to discuss the next phase of Amp, now spun out as its own company. He argues that agents write code, review it, and can push it to main...
canonical: https://daily.dev/posts/orbin-with-amp-changelog-interviews-691--t8ggtafoz
twitter:card: summary_large_image
twitter:site: @dailydotdev
og:type: website
og:site_name: daily.dev
og:title: Orbin' with Amp (Changelog Interviews #691) | daily.dev
og:description: Quinn Slack returns to discuss the next phase of Amp, now spun out as its own company. He argues that agents write code, review it, and can push it to main...
og:url: https://daily.dev/posts/orbin-with-amp-changelog-interviews-691--t8ggtafoz
og:image: https://api.daily.dev/og/posts/T8GGtafoZ.png
og:image:alt: Orbin' with Amp (Changelog Interviews #691)
og:image:width: 1200
og:image:height: 630
og:locale: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Orbin' with Amp (Changelog Interviews #691)

**[Changelog](https://daily.dev/sources/changelog)** · 2 min read · 0 upvotes · 1 comments

## Summary

Quinn Slack returns to discuss the next phase of Amp, now spun out as its own company. He argues that agents write code, review it, and can push it to main themselves, and that code review as we know it is fading. Slack says the underlying AI model matters less than it used to, and raises concerns about losing the open source commons. During the conversation, he builds a feature request live to solve the host's tailnet problem, and discusses 'orbs' and long-lived threads.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://changelog.com/podcast/691>

## Questions this post answers

### Is traditional code review becoming obsolete with AI coding agents like Amp?

Quinn Slack, co-founder of Amp, argues that code review as it's traditionally known is fading because agents now write code, review it themselves, and can push it to main. He suggests the focus is shifting away from manual human review toward trusting agent workflows and long-lived agent 'threads' that retain context over time.

_Developers rethinking review workflows around AI agents can track these shifts on daily.dev._

### Does the choice of AI model matter for coding agent performance?

Quinn Slack states that the underlying AI model matters less than it used to for coding agents like Amp. He frames this as part of a broader shift where the surrounding agent infrastructure, memory, and workflow design matter more than which specific model powers the agent.

_Teams comparing AI coding agents can follow model-versus-infrastructure debates on daily.dev._

## Community discussion

Top comments from developers on daily.dev.

**@nark3d** · 0 upvotes

> When he says code review is fading, is that the human pass going or the gate going?  Those are different bets and the SOC 2 chapter suggests it's the first one, with the agent pushing to main once the checks are green and the human reviewing the policy.  Take a change the checks can't see, like a schema migration that's valid SQL and wrong for the data: what does the orb do with it?

---

Tags: [#open-source](https://daily.dev/tags/open-source), [#ai-agents](https://daily.dev/tags/ai-agents), [#code-review](https://daily.dev/tags/code-review)

[View this post on daily.dev](https://daily.dev/posts/orbin-with-amp-changelog-interviews-691--t8ggtafoz)

```json
{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]}
{"@context":"https://schema.org","@type":"TechArticle","headline":"Orbin' with Amp (Changelog Interviews #691)","url":"https://daily.dev/posts/orbin-with-amp-changelog-interviews-691--t8ggtafoz","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/orbin-with-amp-changelog-interviews-691--t8ggtafoz"},"datePublished":"2026-11-18T22:26:38.069Z","dateModified":"2026-11-18T22:54:31.736Z","description":"Quinn Slack returns to discuss the next phase of Amp, now spun out as its own company. He argues that agents write code, review it, and can push it to main...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/24d8400eda02de8795d260fcc3a38105?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/24d8400eda02de8795d260fcc3a38105?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Changelog","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Changelog","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/f65a74bcb028447aa606f06695d607d3","url":"https://daily.dev/sources/changelog"},"commentCount":1,"discussionUrl":"https://daily.dev/posts/orbin-with-amp-changelog-interviews-691--t8ggtafoz","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":1}],"keywords":"open-source,ai-agents,code-review","timeRequired":"PT2M"}
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Changelog","item":"https://daily.dev/sources/changelog"},{"@type":"ListItem","position":3,"name":"Orbin' with Amp (Changelog Interviews #691)"}]}
{"@context":"https://schema.org","@type":"WebPage","@id":"https://daily.dev/posts/orbin-with-amp-changelog-interviews-691--t8ggtafoz","comment":[{"@type":"Comment","text":"When he says code review is fading, is that the human pass going or the gate going?  Those are different bets and the SOC 2 chapter suggests it’s the first one, with the agent pushing to main once the checks are green and the human reviewing the policy.  Take a change the checks can’t see, like a schema migration that’s valid SQL and wrong for the data: what does the orb do with it?","datePublished":"2026-11-22T17:27:44.319Z","url":"https://daily.dev/posts/T8GGtafoZ#c-dMCAqpJyS","author":{"@type":"Person","name":"Adam","url":"https://daily.dev/nark3d","image":"https://avatars.githubusercontent.com/u/2162621?v=4"}}]}
{"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/orbin-with-amp-changelog-interviews-691--t8ggtafoz#faq","mainEntity":[{"@type":"Question","name":"Is traditional code review becoming obsolete with AI coding agents like Amp?","acceptedAnswer":{"@type":"Answer","text":"Quinn Slack, co-founder of Amp, argues that code review as it's traditionally known is fading because agents now write code, review it themselves, and can push it to main. He suggests the focus is shifting away from manual human review toward trusting agent workflows and long-lived agent 'threads' that retain context over time. Developers rethinking review workflows around AI agents can track these shifts on daily.dev."}},{"@type":"Question","name":"Does the choice of AI model matter for coding agent performance?","acceptedAnswer":{"@type":"Answer","text":"Quinn Slack states that the underlying AI model matters less than it used to for coding agents like Amp. He frames this as part of a broader shift where the surrounding agent infrastructure, memory, and workflow design matter more than which specific model powers the agent. Teams comparing AI coding agents can follow model-versus-infrastructure debates on daily.dev."}}]}
```

