Side Project Spotlight

Steve finally fixed phillycocoa.org, and the journey from broken CircleCI pipelines and hijacked S3 buckets to a blazing-fast Cloudflare Pages site took one Side Project Saturday and an embarrassing number of Codex tokens. Then The Trio turns to the AI hype machine, and they're tired: tired of opaque token costs, tired of reviewing generated code that complicates everything it touches, and tired of an industry that mistakes syntax speed for software engineering. Fred Brooks called it in 1986, and The Trio is calling it now.

## Chapters

00:00 Introductions

01:47 The Journey of Updating the Website

06:38 Challenges with CircleCI and S3 Buckets

09:23 Exploring Cloudflare Pages

11:14 Navigating Cloudflare's User Interface

14:22 Setting Up Automatic Deployments

17:35 Managing DNS and SSL with Cloudflare

23:07 LLM Development Fatigue

26:15 Navigating Concerns and Costs in AI Usage

29:11 LLMs are No Silver Bullet

31:57 The Exhaustion of Code Review and Architectural Decisions

36:25 Token Management and Cost Awareness in AI Tools

40:07 The Economics of AI and Software Development

42:45 The Hype vs. Reality of AI Tools

46:34 Future Prospects of LLMs and Universal UI

50:16 The Future of Edge Computing with LLMs

53:08 The Evolution of Software Development and AI Integration

54:17 AI in Sci-Fi: Myths vs. Reality

57:54 The Challenges of Local Models and Hardware Limitations

01:03:21 Outro & Upcoming Event

01:09:21 Tag

## Show Notes

- Steve spent Side Project Saturday migrating phillycocoa.org from a broken CircleCI/S3 setup to Cloudflare Pages, burning his entire weekly Codex token budget in about three hours.

- Cloudflare Pages handles Hugo builds automatically and manages SSL and CDN without manual config, all on a free tier that's plenty for the site.

- Cloudflare's UI hides the Pages "Get Started" link below giant worker buttons, which Kotaro calls "the weirdest dark pattern."

- Steve argues that syntax generation was never the real bottleneck in software engineering, citing Fred Brooks' 1986 essay "No Silver Bullet."

- Aaron is worn out from reviewing AI-generated code and still having to make every architectural decision himself.

- LLM costs are nearly impossible to forecast: a single prompt can burn a significant chunk of your plan, depending on model, tool calls, and context.

- The Trio sees firms rushing to adopt LLM tooling before the ROI math makes sense, driven by hype rather than evidence.

- ThePrimeagen's recent take on the shifting AI economy lines up with what Steve sees at work: token-based billing is starting to expose the real cost.

- The Trio agrees local models running on personal hardware are the interesting long-term play, but RAM shortages make even basic setups expensive.

- Kotaro closes with a dad joke: he thought his LLM skills landed him his current job, but it turns out...

## Links

**PhillyCocoa.org Update**

Website: https://phillycocoa.org

**Articles & Essays**

"Let's talk about LLMs" by James Bennett: https://www.b-list.org/weblog/2026/apr/09/llms/

"No Silver Bullet" by Fred Brooks: https://www.cs.unc.edu/techreports/86-020.pdf

**Videos**

"The AI economy is about to change" by ThePrimeagen: https://youtu.be/_Q-e_nczWqM

**One More Thing**

"Beyond the Simulator: Perspectives on Modern App Development": https://luma.com/i00ll61z

**PhillyCocoa:** https://phillycocoa.org

Intro music: "When I Hit the Floor", © 2021 Lorne Behrman. Used with permission of the artist.