Episode 010: Where AI Still Breaks

Brendan Buckingham — Mon, 20 Jul 2026 00:00:00 -0400

Two years into building daily with AI, Brendan and Baird check in on what's actually still broken. Baird shares an image-processing pipeline (GPT Image 2, Nano Banana) that nails 8 out of 10 images — then randomly crops the sandwich out of frame. Brendan tells the story of Claude claiming it spun up 10 sub-agents when it actually did the work itself and just said so. They dig into why non-determinism is still the real blocker for hands-off automation, why they're skeptical of "just let the agent loop figure it out," and where AI has genuinely transformed their work: killing activation energy, handling the tedious stuff, and letting them build things they never would have built otherwise.

Thinking about bringing AI into your own work? We're opening up a limited amount of consulting — reach out via the link below.

00:00 Two-year check-in kicks off
02:00 Baird's image-cleanup pipeline: GPT Image 2 vs Nano Banana
05:00 "Fixes" that made it worse — stretched and doubled sandwich
10:00 Nano Banana's silent regeneration limit
12:00 Prompting in English: ambiguity is the real interface problem
14:00 Brendan's Rollbar sub-agent story
15:00 Babysitting scheduled automations
17:00 Why agent loops aren't the answer yet
20:00 Wrapping AI-written scripts to dodge non-determinism
21:00 Activation energy + missing the craft
26:00 Consulting announcement

Sponsor
Powerful podcast hosting & analytics
By podcasters, for podcasters. Since 2016
Brought to you by https://fireside.fm

claudecode #claudeai #aicoding #aiagents

Signup for our newsletter:
https://vibing-with-ai-code.beehiiv.com

Check out our Website
https://vibingwithaicode.com

Episode 004: AI Productivity Systems for Developers: Claude Command Center, and Staying Focused

Brendan Buckingham — Mon, 23 Mar 2026 07:00:00 -0400

After a bit of a hiatus, we are back this week to discuss AI-driven productivity and the challenge of staying focused amid rapidly evolving tools. We compare our approaches to using AI to help with productivity. We also discuss using multiple Claude instances to parallelize bug fixes, the difficulty of review/testing and maintaining understanding, and why safer integrated agent-style tools may beat early open-source alternatives.

Sponsor
Fireside
Powerful podcast hosting & analytics
By podcasters, for podcasters. Since 2016

00:00 Back on the Mic
00:45 AI Productivity Shift
01:35 Email and Slack Triage
03:43 PARA and Daily Priorities
04:37 Analog Cards vs Apps
06:00 AI Surfacing Tasks
08:45 Danger of False Productivity
12:03 Parallelizing Bug Fixes
13:24 Trust and Understanding Gaps
16:34 Acceptance Tests Missing
19:33 Back to Productivity Focus
20:07 Obie Fernandez Prompt System
21:11 Building the Command Center
22:53 Daily Prompts to Slash Commands
27:11 Minimalist Workflow and TickTick
31:02 OpenClaw vs Safer Agents
34:34 Finding the Right UI Layer
37:07 Keeping AI in Its Place
38:34 Wrap Up and Next Steps

ClaudeCode #Windsurf #AICoding #VSCode #CodingTools #AIProgramming

Vibing with AI Code - Episodes Tagged with “Ai Productivity”

Episode 010: Where AI Still Breaks

Episode 004: AI Productivity Systems for Developers: Claude Command Center, and Staying Focused