Quinn Slack on AI Agents: Move Them Off Your Laptop
Quinn Slack explains why running coding agents locally throttles performance, and how Amp uses cloud Orbs to run headless tasks in parallel.
The best ideas from 30+ top podcasts, every week.
Quinn Slack, co-founder of Sourcegraph and founder of Amp, joins to discuss the evolution of AI coding agents and Amp spinning out as an independent, profitable company. They explore why persistent threads and human intent matter more than raw foundational models, how Amp handles cloud agents through Orbs, and why traditional line-by-line code review is fading into artifact verification. Slack also shares his concerns about the erosion of the open-source software commons as developers migrate to siloed private workflows.
Quinn Slack explains why running coding agents locally throttles performance, and how Amp uses cloud Orbs to run headless tasks in parallel.
Quinn Slack explains why AI coding agents make pull requests obsolete and how artifact verification replaces line-by-line code review.
Quinn Slack explains why Amp skipped venture capital, stayed profitable at 20 people, and bets on malleable jelly wear.
Quinn Slack explains why Amp replaced model pickers with intensity dials and swapped 80% of its backend without users noticing.
Quinn Slack explains why Amp writes thread links to Git commits and how preserving immutable prompt logs fixes AI context loss.
Quinn Slack warns that AI code generators and isolated private repositories threaten the open source commons that trained modern coding models.
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.