AI-generated code is no longer just producing low-quality pull requests. According to AWS Principal Engineer and Valkey core maintainer Madelyn Olson, the quality of AI-assisted contributions has improved dramatically in just the last few months.

In this episode of Screaming in the Cloud, Corey Quinn and Madelyn discuss how AI is changing open source development, the growing burden on maintainers, and how projects like Valkey are using AI to find bugs, improve security, and harden production systems. They also explore Valkey's continued growth, the future of software development, and why experience, operational knowledge, and community still matter in an age where code is becoming cheaper to create.

*Since this episode was recorded without video, we thought it was the perfect opportunity to get creative with AI!

Show Highlights:
(00:00) Open Source Stability Push
(00:32) Reinvent Afterglow Banter
(01:40) AI PRs Get Better
(04:36) Whimsy Versus AI Slop
(06:14) AI Security Hunting Reality
(09:12) Maintainers Adapt to AI
(11:28) Valkey Fork Wins Adoption
(14:43) Fighting the AI Tidal Wave
(23:45) Next Five Years and Roadmap
(27:02) Release Woes and Where to Follow

About Madelyn:
Madelyn Olson is a co-creator and core maintainer of Valkey, a high-performance key-value datastore, and a Principal Engineer at Amazon Web Services (AWS). She specializes in building secure, highly reliable systems and is passionate about collaborating with open-source communities. In her role at Amazon, Madelyn serves as a Principal Software Development Engineer for Amazon ElastiCache and Amazon MemoryDB, where she focuses on advancing distributed data technologies and contributing to the growth and success of the Valkey project.

Sponsored by:
duckbillhq.com

What happens when two cloud economists leave AWS behind and spend six days hiking 60 miles on the Appalachian Trail? Corey Quinn sits down with Caleb Hurd to share stories from the trail, including exploding sleeping pads, heroic shuttle drivers, lost phones, and the unique community that makes long-distance hiking special. Along the way, they draw surprising parallels between backpacking and cloud economics, discussing everything from serverless architecture and cloud cost optimization to the hidden challenges of on-prem infrastructure. It's a conversation about technology, adventure, perspective, and why sometimes the best way to solve complex problems is to step away from them entirely.

Show highlights:

(00:00) Why Hiking Hooks You
(00:15) Meet Caleb on the Trail
(01:31) Trail Miles and Ultralight Parallels
(05:24) The Sleeping Pad Blowout
(07:46) Shepherd Saves the Day
(09:43) Trail Community and Cloud Community
(11:07) Post Trail Perspective and Inside Jokes
(15:35) Back to Work On Prem vs Cloud Pain
(25:47) Server-less Spend and Lambda Sprawl
(32:29) Wrap Up Where to Find Caleb

About Caleb:
Caleb Hurd is a Cloud Economist at Duckbill, where he helps enterprises make sense of their cloud spend. Before moving to the cost side of the house, Caleb spent years in the trenches building and operating large-scale cloud environments and leading the engineering teams behind them across companies ranging from healthcare tech to enterprise Saas. He also founded CostOps.cloud, an AWS cost consulting practice, and is a vocal advocate for engineering-led FinOps — arguing that the people closest to the architecture should be the ones driving cost strategy, not spreadsheet jockeys in finance. Caleb holds a degree from Georgia Tech and made an unconventional journey into tech from a background in carpentry, which may explain his preference for building things over just talking about them. He's based in Atlanta.

Links:

LinkedIn: https://www.linkedin.com/in/calebrhurd/

Sponsored by:
duckbillhq.com

In this episode, Corey Quinn sits down with Dexter Horthy, CEO and Co-founder of Human Layer, to unpack what engineers are getting wrong about AI, especially when it comes to coding agents.

From the obsession with “just throwing more tokens at the problem” to the reality of building scalable AI workflows, Dexter shares hard-earned insights on how to actually push models to their limits. They dive into the evolution of developer workflows, the rise of AI-powered software factories, and why understanding context and verification matters more than raw model power.

If you’re building with AI or trying to, this episode will challenge how you think about what these systems can (and can’t) do.

Show highlights:

(00:00)Throwing Tokens Too Far

(01:04) Meet Dexter Horthy

(01:52) Personal AI Benchmarks

(04:12) Human Layer Race Condition

(05:59) Rewrites and Tech Debt

(07:19) Software Factories Mindset

(10:20) Verifiable Problems and Token Limits

(13:45) Agents in the Trenches

(18:05) GitHub at Agent Scale

(26:23) Safety Ethics and Closing Thoughts

About Dexter:

Dexter Horthy is the CEO and Co-Founder of HumanLayer, where he helps engineering teams tackle complex problems in large codebases using coding agents. Previously, he worked in DevOps, SRE, and Solutions Engineering at Replicated, and contributed to lunar navigation software at NASA JPL. Outside of work, he’s a fan of tacos and burpees, though not necessarily in that order.

Links:

LinkedIn: https://www.linkedin.com/in/dexterihorthy/

Website: https://humanlayer.dev

Sponsored by:
duckbillhq.com