Debugging Dan

debuggingdan

Debugging Dan is where I’ll be sharing my personal experiences as I juggle being a husband and a dad, having a full-time job and a passion for side projects. It’s not so much about debugging code, that’s a metaphor. It is about debugging and navigating life in general.

Why start this podcast? For me, it’s about creating a space where we can learn and grow together. Life can get hectic, and side projects can sometimes feel overwhelming. But through this weekly podcast, I hope to offer some guidance, share some laughs, and most importantly, remind you that you’re not alone in this journey.

www.debuggingdan.com

Play

Open in

20 episodes
weekly
Avg 12 min
English

Episodes 20

Newest Oldest Longest

All20 Unplayed20 In progress0 Played0

#49
Yesterday · 9 min
Use AI For Tasks
Dan’s take is: don’t treat AI like a text generator machine. Instead, use it to handle the boring, repetitive stuff and turn your work into actual actions. He argues that future differentiation will come from human communication—AI-generated words/images are getting easier to spot, and the “real you” still matters. But for actionable, repeatable workflows (especially programming and admin tasks), AI can be really powerful—especially with tool-calling, goals/loops, and validation so the work gets checked instead of just outputting words. Stay connected! Follow me on Bluesky at @debuggingdan.com for the latest updates, and subscribe to my YouTube channel @debuggingdan for the podcast and other interesting videos!
- Transcript
#48
August 27 · 2 min
Can You Record a Podcast With a Drone?
Dan talks about how he’s been recording his podcast for fun—at first right at his desk, then switching to recording during his morning walks to get more free time. He’s been doing audio-only since he doesn’t use a camera, so he’s running a new experiment: using a drone to record video while he records his podcast. After seeing a YouTube creator use drones, he picked up an affordable DJI drone and tries to have it track him along the path. It works sometimes, but tracking gets tricky when he isn’t walking straight, and there are other people around, so it’s a bit cumbersome. Stay connected! Follow me on Bluesky at @debuggingdan.com for the latest updates, and subscribe to my YouTube channel @debuggingdan for the podcast and other interesting videos!
- Transcript
#47
August 20 · 5 min
I use AI... Then Don't
Dan talks about how his AI use tends to come in cycles. He’ll go all-in for a while—having AI draft emails and messages, handling a lot of the “communication + creative” stuff—but then his confidence drops. Sometimes he notices the outputs feel off or too generic, so he starts being more critical, revisits drafts, and decides he should write more himself next time. Then, when he’s busy again and the AI feels good enough, he ramps back up and repeats the pattern. He argues AI isn’t really replacing creativity—it supports the process, while the real creative spark still comes from you. He also points out the social/real-world downside: people send “wall of text” emails and Slack messages that could’ve been short and human, and then others have to summarize or filter the mess with AI. He’s curious whether others do the same “cycle,” or just use AI nonstop. Stay connected! Follow me on Bluesky at @debuggingdan.com for the latest updates, and subscribe to my YouTube channel @debuggingdan for the podcast and other interesting videos!
- Transcript
#46
August 13 · 10 min
AI Impact on Live Coding Streams
Dan talks about why he never got around to live-streaming coding much in the past, but lately they’ve been thinking about how it would work now, especially with AI coding/agentic workflows. They bring up an example like Kitze—someone who stopped streaming because sharing the prompts could feel proprietary. Dan wonders how to handle that without making the stream boring, since AI-driven coding often has lots of downtime while the agent runs. Stay connected! Follow me on Bluesky at @debuggingdan.com for the latest updates, and subscribe to my YouTube channel @debuggingdan for the podcast and other interesting videos!
- Transcript
#45
August 8 · 11 min
The Infinite AI frontier
On his daily walk, Dan reflects on the “infinite frontier” of AI: models keep getting updated, and what was great a year ago can suddenly feel behind today. They talk about juggling different model tiers (more expensive “big” models vs cheaper ones) and how people often just YOLO the latest option instead of picking the right tool, until older models get retired and you lose practice with prompt-heavy workflows. Stay connected! Follow me on Bluesky at @debuggingdan.com for the latest updates, and subscribe to my YouTube channel @debuggingdan for the podcast and other interesting videos!
- Transcript
#44
August 1 · 15 min
Avoid AI Lock in
Dan talks on why relying on a single big AI provider is risky — especially from the EU perspective where data rules differ and most innovation (OpenAI, Google, Anthropic, etc.) is US‑based. I cover political/legal exposure, the fragile financing and loss-leading pricing models behind many AI products, and why companies can suddenly stop or pivot products. Stay connected! Follow me on Bluesky at @debuggingdan.com for the latest updates, and subscribe to my YouTube channel @debuggingdan for the podcast and other interesting videos!
- Transcript
#43
July 3 · 13 min
Token limits are getting stricter
Lately it feels like every AI/IDE tool has been changing how you pay—moving away from “credits per chat” to models that charge more directly for compute and use. In this episode, Dan breaks down what’s going on with Anthropic (specifically via Claude/its coding offerings) and why people are annoyed. Stay connected! Follow me on Bluesky at @debuggingdan.com for the latest updates, and subscribe to my YouTube channel @debuggingdan for the podcast and other interesting videos!
- Transcript
#42
June 26 · 10 min
Don't Panic
In this special episode 42 of Debugging Dan, the Dan reflects on Douglas Adams’ Hitchhiker’s Guide to the Galaxy—especially why the number 42 matters and how it’s more about the journey than the actual “answer.” He connects Arthur Dent’s world getting ripped apart (aliens demolishing Earth) to what’s happening in IT right now: AI is basically yanking the rug out from under devs, and everyone’s scrambling to find a workable direction. Stay connected! Follow me on Bluesky at @debuggingdan.com for the latest updates, and subscribe to my YouTube channel @debuggingdan for the podcast and other interesting videos!
- Transcript
#41
May 13 · 15 min
Building a Second Brain
On this episode, Dan talks about the “second brain” idea—basically a system (think Notion/Obsidian) for saving info so an AI can pull it up later and also help turn old content into new documents. They describe a simple setup: store Markdown (or ingest things like PDFs/MP4s and auto-transcribe them into Markdown), organize everything in a folder structure, and use an “agent” to summarize, search, and even draft things like statements of work or design docs from what it finds. Stay connected! Follow me on Bluesky at @debuggingdan.com for the latest updates, and subscribe to my YouTube channel @debuggingdan for the podcast and other interesting videos!
- Transcript
#40
April 30 · 11 min
Using Free Github Compute
Dan explains how he uses GitHub Actions for non-code tasks—specifically automating his podcast workflow. He wires up n8n and a Telegram bot to trigger GitHub workflows that run FFmpeg to generate thumbnails, stitch images to audio for YouTube, and extract short clips. Benefits: no VPS, easy edits (even on a phone), free runner minutes and downloadable artifacts (30-day retention). Stay connected! Follow me on Bluesky at @debuggingdan.com for the latest updates, and subscribe to my YouTube channel @debuggingdan for the podcast and other interesting videos!
- Transcript
#39
April 23 · 14 min
Is the AI Bubble Cracking?
Dan breaks down a bunch of recent signs that the “AI” honeymoon might be ending—mostly driven by compute capacity getting tight. He points to examples like GitHub Copilot pausing new subscriptions and possibly tightening usage limits, plus Anthropic experimenting with reduced session limits and even selling plans that exclude certain features. On top of that, the Cursor/AnySphere news hints at big compute partnerships (via SpaceX/XAI), which could mean more momentum—but also more dependence on a smaller set of players. Stay connected! Follow me on Bluesky at @debuggingdan.com for the latest updates, and subscribe to my YouTube channel @debuggingdan for the podcast and other interesting videos!
- Transcript
#38
April 5 · 10 min
AI at an Agency vs Other Company Types
Dan records a foggy-morning rant about why AI-assisted coding feels like two different worlds: the fast, messy freedom of bootstrapped solo projects versus the slower, controlled pace of agency work. Stay connected! Follow me on Bluesky at @debuggingdan.com for the latest updates, and subscribe to my YouTube channel @debuggingdan for the podcast and other interesting videos!
- Transcript
#37
March 30 · 19 min
What I learned about P2P
Dan takes a stroll and thinks out loud about peer-to-peer networking. Thinking about using P2P to connect AI agents and unpacking how these systems actually find each other. I run through history (Napster, BitTorrent, IPFS) and talk about the practical building blocks: local discovery (mDNS/Bonjour), bootstrap nodes (preconfigured always-on peers), and why you usually need at least some reachable node to get started. Stay connected! Follow me on Bluesky at @debuggingdan.com for the latest updates, and subscribe to my YouTube channel @debuggingdan for the podcast and other interesting videos!
- Transcript
#36
March 24 · 19 min
Standalone AI Agents
Dan digs into “standalone” AI agents—agents you kick off with a goal and they go figure it out without you babysitting them. He talks through building a DIY orchestration setup with a “composer/conductor” agent that breaks work into subtasks and hands them to sub-agents (great for parallelizing work and keeping the main agent’s context clean). Along the way he runs into the real pain points: getting prompts tight enough to stop agents from being super chatty, dealing with local models that struggle with instruction-following, and weighing the tradeoffs. Stay connected! Follow me on Bluesky at @debuggingdan.com for the latest updates, and subscribe to my YouTube channel @debuggingdan for the podcast and other interesting videos!
- Transcript
#35
March 20 · 14 min
IDEs and love for Zed
Dan talks abouto how the IDE/editor space is shifting fast thanks to AI/agentic dev. VS Code (and its open-ish Monaco/Electron base) has spawned a bunch of forks like Cursor, Windsurf, etc., but those forks can get messy: licensing limits on certain Microsoft extensions, plugin compatibility drift, and breakages (like Prettier/ESM issues) as the fork falls out of sync with upstream. Stay connected! Follow me on Bluesky at @debuggingdan.com for the latest updates, and subscribe to my YouTube channel @debuggingdan for the podcast and other interesting videos!
- Transcript
#34
March 15 · 17 min
Openclaw, some critical notes
Dan takes OpenCLAW for a spin—well, more like a skeptical walk-and-talk about why everyone’s suddenly hyped on it. He breaks down what it actually is (an agent framework that can run tools, hit the command line, and use your LLM API keys to do work autonomously), why folks isolate it on a Mac mini or VPS, and where the sharp edges are. Stay connected! Follow me on Bluesky at @debuggingdan.com for the latest updates, and subscribe to my YouTube channel @debuggingdan for the podcast and other interesting videos!
- Transcript
#33
March 10 · 15 min
Podcast recording using n8n and AI
This episode is basically a “how do I stop freezing up when I record solo?” brain dump—recorded on a morning walk. Dan talks about the weird invisible hurdle of starting (talking to yourself outside at 6:30am is… a vibe), and how most podcasts feel easier because they’re conversations. So Dan created a workaround: record in short chunks, send the audio to a Telegram bot that transcribes it and asks follow-up questions via AI, then use those prompts to keep the episode moving and go deeper. Stay connected! Follow me on Bluesky at @debuggingdan.com for the latest updates, and subscribe to my YouTube channel @debuggingdan for the podcast and other interesting videos!
- Transcript
#32
March 3 · 14 min
Decentralized AI Agents
Dan talks on the “next level” of autonomous AI agents after chatting with colleagues about OpenClaw (agent harness + gateway + Slack/Discord-style messaging). He breaks down what’s cool (teams of agents that browse the web, run terminal commands, coordinate work) and what’s scary (huge security risk: autonomous agents + prompt-injection sites could lead to data leaks or malware). The big idea: simplify the whole gateway/VPN/tunnel setup by having agents discover and talk to each other over a peer-to-peer network instead. Stay connected! Follow me on Bluesky at @debuggingdan.com for the latest updates, and subscribe to my YouTube channel @debuggingdan for the podcast and other interesting videos!
- Transcript
#31
February 28 · 4 min
A Refreshed Podcast
Dan’s back after a hiatus! He ditched the studio (and side-project burnout) to record this rebooted podcast during his daily walks. No fancy setups — just earbuds, noise reduction, and outdoor vibes. Expect casual chats about his current tech obsessions: AI coding with tools like Cursor/Copilot, automation workflows (n8n fans, rejoice!), and the wild world of AI agents. He’ll share work learnings, tech experiments, and random brain dumps. No video, but YouTube visuals will tag along. Subscribe if you’re into unfiltered tech musings! Stay connected! Follow me on Bluesky at @debuggingdan.com for the latest updates, and subscribe to my YouTube channel @debuggingdan for the podcast and other interesting videos!
- Transcript
#30
Apr 18, 2025 · 12 min
My Take on Vibe Coding
In this episode of the Debugging Dan podcast, I dive into the concept of Vibe Coding, my unique interpretation of coding with the assistance of AI. I discuss how Vibe Coding makes it easier for people, regardless of their coding knowledge, to build applications using AI-driven tools like Vercel and Cursor. I’ve noticed an increase in AI-written posts on forums, where creators showcase quick projects that they’ve built, often motivated by the desire to gain recognition rather than contribute meaningful content. I share my personal experiences with using AI for coding, the challenges of prompting effectively, and my current focus on content generation through N8N—a no-code tool I’m enjoying. Vibe Coding, for me, represents following the flow and working with enthusiasm rather than getting bogged down by large projects. Stay connected! Follow me on Bluesky at @debuggingdan.com for the latest updates, and subscribe to my YouTube channel @debuggingdan for the podcast and other interesting videos!
- Transcript

Showing 1–20 of 20 episodes