{"version":"https://jsonfeed.org/version/1","title":"Vibing with AI Code","home_page_url":"https://vibing-with-ai-code.fireside.fm","feed_url":"https://vibing-with-ai-code.fireside.fm/json","description":"We are here to discuss the latest in the world of coding with AI. We explore both the good and the bad, and help you make informed decisions based on our experiences. A key component of this channel is sharing what we learn, to improve both our skills and yours. Let's grow together!","_fireside":{"subtitle":"Follow Us on AI Coding Journey","pubdate":"2026-08-05T00:00:00.000-04:00","explicit":false,"owner":"Brendan Buckingham","image":"https://media24.fireside.fm/file/fireside-images-2024/podcasts/images/c/c8a4ad2b-dfe8-44f3-9a66-0f0713ee3407/cover.jpg?v=1"},"items":[{"id":"1b8fdf15-d882-497b-9d94-7cdbf89fea6a","title":"Episode 012: The Plan Matters More Than the Model","url":"https://vibing-with-ai-code.fireside.fm/012","content_text":"With Fable's Pro-plan window closing, Brendan and Baird both did the same thing on their own: instead of trying to build with it, they had Fable plan — full roadmaps and individual feature specs — so cheaper models like Opus and Sonnet could execute against a high-quality plan. That kicks off a wider check-in on where AI is actually landing right now.  Models feeling far more thorough and meticulous, Opus writing Python scripts to verify Ruby physics it can't run, Claude Code's improved auto-permissions mode finally letting you kick off work and walk away, and why agent loops still aren't the answer when there's no clear \"right\" to test against — especially for subjective frontend and design work. They close on the real distinction that's going to matter: AI is a tool that fills gaps you couldn't otherwise fill, but take the human out and all you've got is slop.\n\nSponsor\nPowerful podcast hosting \u0026amp; analytics\nBy podcasters, for podcasters. Since 2016\nBrought to you by https://fireside.fm\n\nclaudecode  #claudeai #aicoding #aiagents\n\nSignup for our newsletter:\nhttps://vibing-with-ai-code.beehiiv.com\n\nCheck out our Website\nhttps://vibingwithaicode.com","content_html":"\u003cp\u003eWith Fable's Pro-plan window closing, Brendan and Baird both did the same thing on their own: instead of trying to build with it, they had Fable plan — full roadmaps and individual feature specs — so cheaper models like Opus and Sonnet could execute against a high-quality plan. That kicks off a wider check-in on where AI is actually landing right now.  Models feeling far more thorough and meticulous, Opus writing Python scripts to verify Ruby physics it can't run, Claude Code's improved auto-permissions mode finally letting you kick off work and walk away, and why agent loops still aren't the answer when there's no clear \"right\" to test against — especially for subjective frontend and design work. They close on the real distinction that's going to matter: AI is a tool that fills gaps you couldn't otherwise fill, but take the human out and all you've got is slop.\u003c/p\u003e\n\n\u003cp\u003e\u003cstrong\u003eSponsor\u003c/strong\u003e\u003cbr\u003e\nPowerful podcast hosting \u0026amp; analytics\u003cbr\u003e\nBy podcasters, for podcasters. Since 2016\u003cbr\u003e\nBrought to you by \u003ca href=\"https://fireside.fm\" rel=\"nofollow noopener\"\u003ehttps://fireside.fm\u003c/a\u003e\u003c/p\u003e\n\nclaudecode  #claudeai #aicoding #aiagents\n\n\u003cp\u003eSignup for our newsletter:\u003cbr\u003e\n\u003ca href=\"https://vibing-with-ai-code.beehiiv.com\" rel=\"nofollow noopener\"\u003ehttps://vibing-with-ai-code.beehiiv.com\u003c/a\u003e\u003c/p\u003e\n\n\u003cp\u003eCheck out our Website\u003cbr\u003e\n\u003ca href=\"https://vibingwithaicode.com\" rel=\"nofollow noopener\"\u003ehttps://vibingwithaicode.com\u003c/a\u003e\u003c/p\u003e","summary":"","date_published":"2026-08-05T00:00:00.000-04:00","attachments":[{"url":"https://aphid.fireside.fm/d/1437767933/c8a4ad2b-dfe8-44f3-9a66-0f0713ee3407/1b8fdf15-d882-497b-9d94-7cdbf89fea6a.mp3","mime_type":"audio/mpeg","size_in_bytes":44246038,"duration_in_seconds":2765}]},{"id":"fb272243-3967-4875-b58b-68012c9691e2","title":"Episode 011: Activation Energy: How AI Gets You Back Into Old Projects","url":"https://vibing-with-ai-code.fireside.fm/011","content_text":"Brendan dove back into three stalled projects in one day — a personal command center, a video game tracker, and a Rails 8 app he hadn't touched in two months — and both hosts dig into why AI makes restarting old projects so much easier: it remembers where you left off, tells you what's actually built, and (with Fable) plans and cross-checks the reassessment before you write a line of code. They get into when it's worth splitting context (personal vs. project-specific memory), why Fable feels like the best planner but not necessarily the best daily driver, and how tools like Conductor now auto-select models per task. Plus: what actually happens when sub-agents run out of session usage mid-task, and why lowering activation energy might be the single biggest thing AI has changed about how they work.\n\nSponsor\nPowerful podcast hosting \u0026amp; analytics\nBy podcasters, for podcasters. Since 2016\nBrought to you by https://fireside.fm\n\nclaudecode  #claudeai #aicoding #aiagents\n\nSignup for our newsletter:\nhttps://vibing-with-ai-code.beehiiv.com\n\nCheck out our Website\nhttps://vibingwithaicode.com","content_html":"\u003cp\u003eBrendan dove back into three stalled projects in one day — a personal command center, a video game tracker, and a Rails 8 app he hadn't touched in two months — and both hosts dig into why AI makes restarting old projects so much easier: it remembers where you left off, tells you what's actually built, and (with Fable) plans and cross-checks the reassessment before you write a line of code. They get into when it's worth splitting context (personal vs. project-specific memory), why Fable feels like the best planner but not necessarily the best daily driver, and how tools like Conductor now auto-select models per task. Plus: what actually happens when sub-agents run out of session usage mid-task, and why lowering activation energy might be the single biggest thing AI has changed about how they work.\u003c/p\u003e\n\n\u003cp\u003e\u003cstrong\u003eSponsor\u003c/strong\u003e\u003cbr\u003e\nPowerful podcast hosting \u0026amp; analytics\u003cbr\u003e\nBy podcasters, for podcasters. Since 2016\u003cbr\u003e\nBrought to you by \u003ca href=\"https://fireside.fm\" rel=\"nofollow noopener\"\u003ehttps://fireside.fm\u003c/a\u003e\u003c/p\u003e\n\nclaudecode  #claudeai #aicoding #aiagents\n\n\u003cp\u003eSignup for our newsletter:\u003cbr\u003e\n\u003ca href=\"https://vibing-with-ai-code.beehiiv.com\" rel=\"nofollow noopener\"\u003ehttps://vibing-with-ai-code.beehiiv.com\u003c/a\u003e\u003c/p\u003e\n\n\u003cp\u003eCheck out our Website\u003cbr\u003e\n\u003ca href=\"https://vibingwithaicode.com\" rel=\"nofollow noopener\"\u003ehttps://vibingwithaicode.com\u003c/a\u003e\u003c/p\u003e","summary":"","date_published":"2026-07-27T00:00:00.000-04:00","attachments":[{"url":"https://aphid.fireside.fm/d/1437767933/c8a4ad2b-dfe8-44f3-9a66-0f0713ee3407/fb272243-3967-4875-b58b-68012c9691e2.mp3","mime_type":"audio/mpeg","size_in_bytes":32787269,"duration_in_seconds":2049}]},{"id":"cfec6fa2-0288-48c4-85ee-4dbbc7c5d6f6","title":"Episode 010: Where AI Still Breaks","url":"https://vibing-with-ai-code.fireside.fm/010","content_text":"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.\n\nThinking about bringing AI into your own work? We're opening up a limited amount of consulting — reach out via the link below.\n\n00:00 Two-year check-in kicks off\n02:00 Baird's image-cleanup pipeline: GPT Image 2 vs Nano Banana\n05:00 \"Fixes\" that made it worse — stretched and doubled sandwich\n10:00 Nano Banana's silent regeneration limit\n12:00 Prompting in English: ambiguity is the real interface problem\n14:00 Brendan's Rollbar sub-agent story\n15:00 Babysitting scheduled automations\n17:00 Why agent loops aren't the answer yet\n20:00 Wrapping AI-written scripts to dodge non-determinism\n21:00 Activation energy + missing the craft\n26:00 Consulting announcement\n\nSponsor\nPowerful podcast hosting \u0026amp; analytics\nBy podcasters, for podcasters. Since 2016\nBrought to you by https://fireside.fm\n\nclaudecode  #claudeai #aicoding #aiagents\n\nSignup for our newsletter:\nhttps://vibing-with-ai-code.beehiiv.com\n\nCheck out our Website\nhttps://vibingwithaicode.com","content_html":"\u003cp\u003eTwo 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.\u003c/p\u003e\n\n\u003cp\u003eThinking about bringing AI into your own work? We're opening up a limited amount of consulting — reach out via the link below.\u003c/p\u003e\n\n\u003cp\u003e00:00 Two-year check-in kicks off\u003cbr\u003e\n02:00 Baird's image-cleanup pipeline: GPT Image 2 vs Nano Banana\u003cbr\u003e\n05:00 \"Fixes\" that made it worse — stretched and doubled sandwich\u003cbr\u003e\n10:00 Nano Banana's silent regeneration limit\u003cbr\u003e\n12:00 Prompting in English: ambiguity is the real interface problem\u003cbr\u003e\n14:00 Brendan's Rollbar sub-agent story\u003cbr\u003e\n15:00 Babysitting scheduled automations\u003cbr\u003e\n17:00 Why agent loops aren't the answer yet\u003cbr\u003e\n20:00 Wrapping AI-written scripts to dodge non-determinism\u003cbr\u003e\n21:00 Activation energy + missing the craft\u003cbr\u003e\n26:00 Consulting announcement\u003c/p\u003e\n\n\u003cp\u003e\u003cstrong\u003eSponsor\u003c/strong\u003e\u003cbr\u003e\nPowerful podcast hosting \u0026amp; analytics\u003cbr\u003e\nBy podcasters, for podcasters. Since 2016\u003cbr\u003e\nBrought to you by \u003ca href=\"https://fireside.fm\" rel=\"nofollow noopener\"\u003ehttps://fireside.fm\u003c/a\u003e\u003c/p\u003e\n\nclaudecode  #claudeai #aicoding #aiagents\n\n\u003cp\u003eSignup for our newsletter:\u003cbr\u003e\n\u003ca href=\"https://vibing-with-ai-code.beehiiv.com\" rel=\"nofollow noopener\"\u003ehttps://vibing-with-ai-code.beehiiv.com\u003c/a\u003e\u003c/p\u003e\n\n\u003cp\u003eCheck out our Website\u003cbr\u003e\n\u003ca href=\"https://vibingwithaicode.com\" rel=\"nofollow noopener\"\u003ehttps://vibingwithaicode.com\u003c/a\u003e\u003c/p\u003e","summary":"","date_published":"2026-07-20T00:00:00.000-04:00","attachments":[{"url":"https://aphid.fireside.fm/d/1437767933/c8a4ad2b-dfe8-44f3-9a66-0f0713ee3407/cfec6fa2-0288-48c4-85ee-4dbbc7c5d6f6.mp3","mime_type":"audio/mpeg","size_in_bytes":27035348,"duration_in_seconds":1607}]},{"id":"d87ba8ae-d0cb-418b-a816-32067fd454e8","title":"Episode 009: How to Get Bespoke AI Design (Without Being a Designer)","url":"https://vibing-with-ai-code.fireside.fm/009","content_text":"AI design is getting better — but it's also getting more homogenous. First it was the Tailwind default. Now it's the Claude Design default. In this episode, Baird walks through how he rebuilt his personal portfolio site using a design-systems approach with AI skills — and why that process produces something that actually feels intentional.\n\nSponsor\nPowerful podcast hosting \u0026amp; analytics\nBy podcasters, for podcasters. Since 2016\nBrought to you by https://fireside.fm\n\nclaudecode #claudeai #aidesign #aicoding #aiagents","content_html":"\u003cp\u003eAI design is getting better — but it's also getting more homogenous. First it was the Tailwind default. Now it's the Claude Design default. In this episode, Baird walks through how he rebuilt his personal portfolio site using a design-systems approach with AI skills — and why that process produces something that actually feels intentional.\u003c/p\u003e\n\n\u003cp\u003e\u003cstrong\u003eSponsor\u003c/strong\u003e\u003cbr\u003e\nPowerful podcast hosting \u0026amp; analytics\u003cbr\u003e\nBy podcasters, for podcasters. Since 2016\u003cbr\u003e\nBrought to you by \u003ca href=\"https://fireside.fm\" rel=\"nofollow noopener\"\u003ehttps://fireside.fm\u003c/a\u003e\u003c/p\u003e\n\nclaudecode #claudeai #aidesign #aicoding #aiagents","summary":"","date_published":"2026-06-24T10:00:00.000-04:00","attachments":[{"url":"https://aphid.fireside.fm/d/1437767933/c8a4ad2b-dfe8-44f3-9a66-0f0713ee3407/d87ba8ae-d0cb-418b-a816-32067fd454e8.mp3","mime_type":"audio/mpeg","size_in_bytes":22767635,"duration_in_seconds":1340}]},{"id":"dc9e2ddd-35b2-49a0-83ce-e7a90bc1ee66","title":"Episode 008: AI Coding Tools Are Getting More Expensive: How to Adapt with Models, Harnesses, and Skills","url":"https://vibing-with-ai-code.fireside.fm/008","content_text":"The hosts discuss the rising costs and tightening limits for AI tools as companies try to recoup massive infrastructure spending. They note signs that features like Claude Code may be removed from the $20/month Pro plan. They compare experiences hitting usage caps faster when using agent-style workflows like the “Get Shit Done” framework, which can burn tokens quickly especially during planning. To cope, they describe mixing tools and models—Claude Code, OpenAI Codex, Windsurf, and free alternatives like Kimi—using cheaper models for research or simple tasks and reserving premium models for complex work. They also explore switching costs from tool ecosystems, differences between models and harnesses, and how reusable “skills” (often just markdown files) can improve reliability across platforms and help users stay productive on a budget.\n\nSponsor\nPowerful podcast hosting \u0026amp; analytics\nBy podcasters, for podcasters. Since 2016\nBrought to you by https://fireside.fm\n\nclaudecode  #claudeai #aicoding #aiagents\n\nSignup for our newsletter:\nhttps://vibing-with-ai-code.beehiiv.com\n\nCheck out our Website\nhttps://vibingwithaicode.com","content_html":"\u003cp\u003eThe hosts discuss the rising costs and tightening limits for AI tools as companies try to recoup massive infrastructure spending. They note signs that features like Claude Code may be removed from the $20/month Pro plan. They compare experiences hitting usage caps faster when using agent-style workflows like the “Get Shit Done” framework, which can burn tokens quickly especially during planning. To cope, they describe mixing tools and models—Claude Code, OpenAI Codex, Windsurf, and free alternatives like Kimi—using cheaper models for research or simple tasks and reserving premium models for complex work. They also explore switching costs from tool ecosystems, differences between models and harnesses, and how reusable “skills” (often just markdown files) can improve reliability across platforms and help users stay productive on a budget.\u003c/p\u003e\n\n\u003cp\u003e\u003cstrong\u003eSponsor\u003c/strong\u003e\u003cbr\u003e\nPowerful podcast hosting \u0026amp; analytics\u003cbr\u003e\nBy podcasters, for podcasters. Since 2016\u003cbr\u003e\nBrought to you by \u003ca href=\"https://fireside.fm\" rel=\"nofollow noopener\"\u003ehttps://fireside.fm\u003c/a\u003e\u003c/p\u003e\n\nclaudecode  #claudeai #aicoding #aiagents\n\n\u003cp\u003eSignup for our newsletter:\u003cbr\u003e\n\u003ca href=\"https://vibing-with-ai-code.beehiiv.com\" rel=\"nofollow noopener\"\u003ehttps://vibing-with-ai-code.beehiiv.com\u003c/a\u003e\u003c/p\u003e\n\n\u003cp\u003eCheck out our Website\u003cbr\u003e\n\u003ca href=\"https://vibingwithaicode.com\" rel=\"nofollow noopener\"\u003ehttps://vibingwithaicode.com\u003c/a\u003e\u003c/p\u003e","summary":"","date_published":"2026-04-26T20:00:00.000-04:00","attachments":[{"url":"https://aphid.fireside.fm/d/1437767933/c8a4ad2b-dfe8-44f3-9a66-0f0713ee3407/dc9e2ddd-35b2-49a0-83ce-e7a90bc1ee66.mp3","mime_type":"audio/mpeg","size_in_bytes":23647511,"duration_in_seconds":1395}]},{"id":"4636ae35-62bd-4094-9561-296f609d0667","title":"Episode 007: Claude Dispatch Update and Building Local AI Agents with Gemma 4","url":"https://vibing-with-ai-code.fireside.fm/007","content_text":"In this episode, the hosts share a hands-on update on using Claude Dispatch.  They discuss how it works as a separate synced chat that can trigger and check on jobs remotely, create tickets from analysis results, and request new agents.  They also reference the current friction around permissions and repository selection. The conversation then shifts to exploring local and lower-cost agentic AI workflows due to usage limits and subscription costs, including experimenting with Google’s Gemma 4 as a local “brain” via LM Studio and using Kimi in Windsurf to build a new local agent app (code-named “Loki”) with chat, tools, memory, and research capabilities.\n\nSponsor\nFireside\nPowerful podcast hosting \u0026amp; analytics\nBy podcasters, for podcasters. Since 2016\n\nSign up for our newsletter\nCheck out our Website\n\n00:00 Dispatch Update Kickoff\n01:10 What Dispatch Can Do\n03:04 Poolside Rollbar Workflow\n05:37 Dispatch Integration Questions\n08:35 Rethinking Work With Agents\n13:50 Claude Limits Spark Local Shift\n15:26 Gemma 4 Local Agent App\n18:32 Building The Framework Fast\n22:52 Tauri Local First Architecture\n27:43 Model Switching And Cost Hacks\n30:58 Loki Next Steps Wrap Up","content_html":"\u003cp\u003eIn this episode, the hosts share a hands-on update on using Claude Dispatch.  They discuss how it works as a separate synced chat that can trigger and check on jobs remotely, create tickets from analysis results, and request new agents.  They also reference the current friction around permissions and repository selection. The conversation then shifts to exploring local and lower-cost agentic AI workflows due to usage limits and subscription costs, including experimenting with Google’s Gemma 4 as a local “brain” via LM Studio and using Kimi in Windsurf to build a new local agent app (code-named “Loki”) with chat, tools, memory, and research capabilities.\u003c/p\u003e\n\n\u003cp\u003e\u003cstrong\u003eSponsor\u003c/strong\u003e\u003cbr\u003e\n\u003ca href=\"https://fireside.fm\" rel=\"nofollow noopener\"\u003eFireside\u003c/a\u003e\u003cbr\u003e\nPowerful podcast hosting \u0026amp; analytics\u003cbr\u003e\nBy podcasters, for podcasters. Since 2016\u003c/p\u003e\n\n\u003cp\u003e\u003ca href=\"https://vibing-with-ai-code.beehiiv.com/\" rel=\"nofollow noopener\"\u003eSign up for our newsletter\u003c/a\u003e\u003cbr\u003e\n\u003ca href=\"https://vibingwithaicode.com\" rel=\"nofollow noopener\"\u003eCheck out our Website\u003c/a\u003e\u003c/p\u003e\n\n\u003cp\u003e00:00 Dispatch Update Kickoff\u003cbr\u003e\n01:10 What Dispatch Can Do\u003cbr\u003e\n03:04 Poolside Rollbar Workflow\u003cbr\u003e\n05:37 Dispatch Integration Questions\u003cbr\u003e\n08:35 Rethinking Work With Agents\u003cbr\u003e\n13:50 Claude Limits Spark Local Shift\u003cbr\u003e\n15:26 Gemma 4 Local Agent App\u003cbr\u003e\n18:32 Building The Framework Fast\u003cbr\u003e\n22:52 Tauri Local First Architecture\u003cbr\u003e\n27:43 Model Switching And Cost Hacks\u003cbr\u003e\n30:58 Loki Next Steps Wrap Up\u003c/p\u003e","summary":"","date_published":"2026-04-15T22:00:00.000-04:00","attachments":[{"url":"https://aphid.fireside.fm/d/1437767933/c8a4ad2b-dfe8-44f3-9a66-0f0713ee3407/4636ae35-62bd-4094-9561-296f609d0667.mp3","mime_type":"audio/mpeg","size_in_bytes":30454262,"duration_in_seconds":1903}]},{"id":"1a384a7d-8459-404d-844c-a8aa15cd6925","title":"Episode 006: Claude Cowork Scheduling \u0026 Permissions: Fixing Friction in Autonomous AI Workflows","url":"https://vibing-with-ai-code.fireside.fm/006","content_text":"In this episode, the hosts discuss practical challenges with Claude Cowork and scheduled AI jobs, focusing on friction points like needing a laptop to be awake for tasks to run, inconsistent scheduling behavior, and recurring permission prompts that can silently halt background workflows.\n\nSponsor\nFireside\nPowerful podcast hosting \u0026amp; analytics\nBy podcasters, for podcasters. Since 2016\n\nSign up for our newsletter\n\n00:19 Show Format And Goals\n01:25 Claude Cowork Friction\n01:59 Scheduling And Permissions\n06:43 Dashboard And Tool Sprawl\n08:08 Dispatch Mobile Layer\n09:46 Live Debug With Claude\n15:39 Global Bypass Is Risky\n20:37 Whitelist The Middle Ground\n24:17 Wrap Up And Subscribe","content_html":"\u003cp\u003eIn this episode, the hosts discuss practical challenges with Claude Cowork and scheduled AI jobs, focusing on friction points like needing a laptop to be awake for tasks to run, inconsistent scheduling behavior, and recurring permission prompts that can silently halt background workflows.\u003c/p\u003e\n\n\u003cp\u003e\u003cstrong\u003eSponsor\u003c/strong\u003e\u003cbr\u003e\n\u003ca href=\"https://fireside.fm\" rel=\"nofollow noopener\"\u003eFireside\u003c/a\u003e\u003cbr\u003e\nPowerful podcast hosting \u0026amp; analytics\u003cbr\u003e\nBy podcasters, for podcasters. Since 2016\u003c/p\u003e\n\n\u003cp\u003e\u003ca href=\"https://vibing-with-ai-code.beehiiv.com/\" rel=\"nofollow noopener\"\u003eSign up for our newsletter\u003c/a\u003e\u003c/p\u003e\n\n\u003cp\u003e00:19 Show Format And Goals\u003cbr\u003e\n01:25 Claude Cowork Friction\u003cbr\u003e\n01:59 Scheduling And Permissions\u003cbr\u003e\n06:43 Dashboard And Tool Sprawl\u003cbr\u003e\n08:08 Dispatch Mobile Layer\u003cbr\u003e\n09:46 Live Debug With Claude\u003cbr\u003e\n15:39 Global Bypass Is Risky\u003cbr\u003e\n20:37 Whitelist The Middle Ground\u003cbr\u003e\n24:17 Wrap Up And Subscribe\u003c/p\u003e","summary":"","date_published":"2026-04-06T06:00:00.000-04:00","attachments":[{"url":"https://aphid.fireside.fm/d/1437767933/c8a4ad2b-dfe8-44f3-9a66-0f0713ee3407/1a384a7d-8459-404d-844c-a8aa15cd6925.mp3","mime_type":"audio/mpeg","size_in_bytes":23966699,"duration_in_seconds":1497}]},{"id":"edc30fa7-97d7-4231-a737-28acccf606cc","title":"Episode 005: AI Liability \u0026 Vibe Coding: Security, Safeguards, and Best Practices for Founders","url":"https://vibing-with-ai-code.fireside.fm/005","content_text":"AI is powerful but risky in the wrong hands. We break down the real liability and security concerns founders face when using LLMs in local development — from overly permissive \"YOLO mode\" to production database wipeouts. Plus practical best practices for vibe coders who want to ship fast without blowing up their app.\n\nSponsor\nFireside\nPowerful podcast hosting \u0026amp; analytics\nBy podcasters, for podcasters. Since 2016\n\nLink to The Bootstrapped Founder episode we discussed\n\nSign up for our newsletter\n\n00:00 AI News Overload\n00:59 Podscan and Liability\n02:21 YOLO Mode Dangers\n04:17 Vibe Coding Blind Spots\n08:38 Permission Prompt Fatigue\n13:02 Sandboxing and Open Source\n15:00 API Lockdowns and Best Practices\n16:49 Avoiding Surprise Bills\n23:03 Advice for New Vibe Coders\n25:10 Code Reviews and Security Audits\n28:39 Wrap Up and Newsletter","content_html":"\u003cp\u003eAI is powerful but risky in the wrong hands. We break down the real liability and security concerns founders face when using LLMs in local development — from overly permissive \"YOLO mode\" to production database wipeouts. Plus practical best practices for vibe coders who want to ship fast without blowing up their app.\u003c/p\u003e\n\n\u003cp\u003e\u003cstrong\u003eSponsor\u003c/strong\u003e\u003cbr\u003e\n\u003ca href=\"https://fireside.fm\" rel=\"nofollow noopener\"\u003eFireside\u003c/a\u003e\u003cbr\u003e\nPowerful podcast hosting \u0026amp; analytics\u003cbr\u003e\nBy podcasters, for podcasters. Since 2016\u003c/p\u003e\n\n\u003cp\u003e\u003ca href=\"https://thebootstrappedfounder.com/ai-liability-the-landmines-under-your-saas/\" rel=\"nofollow noopener\"\u003eLink to The Bootstrapped Founder episode we discussed\u003c/a\u003e\u003c/p\u003e\n\n\u003cp\u003e\u003ca href=\"https://vibing-with-ai-code.beehiiv.com/\" rel=\"nofollow noopener\"\u003eSign up for our newsletter\u003c/a\u003e\u003c/p\u003e\n\n\u003cp\u003e00:00 AI News Overload\u003cbr\u003e\n00:59 Podscan and Liability\u003cbr\u003e\n02:21 YOLO Mode Dangers\u003cbr\u003e\n04:17 Vibe Coding Blind Spots\u003cbr\u003e\n08:38 Permission Prompt Fatigue\u003cbr\u003e\n13:02 Sandboxing and Open Source\u003cbr\u003e\n15:00 API Lockdowns and Best Practices\u003cbr\u003e\n16:49 Avoiding Surprise Bills\u003cbr\u003e\n23:03 Advice for New Vibe Coders\u003cbr\u003e\n25:10 Code Reviews and Security Audits\u003cbr\u003e\n28:39 Wrap Up and Newsletter\u003c/p\u003e","summary":"","date_published":"2026-03-30T06:00:00.000-04:00","attachments":[{"url":"https://aphid.fireside.fm/d/1437767933/c8a4ad2b-dfe8-44f3-9a66-0f0713ee3407/edc30fa7-97d7-4231-a737-28acccf606cc.mp3","mime_type":"audio/mpeg","size_in_bytes":28216192,"duration_in_seconds":1763}]},{"id":"cd30394e-07d8-4288-a2b1-c26b844ad52e","title":"Episode 004: AI Productivity Systems for Developers: Claude Command Center, and Staying Focused","url":"https://vibing-with-ai-code.fireside.fm/004","content_text":"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.\n\nSponsor\nFireside\nPowerful podcast hosting \u0026amp; analytics\nBy podcasters, for podcasters. Since 2016\n\n00:00 Back on the Mic\n00:45 AI Productivity Shift\n01:35 Email and Slack Triage\n03:43 PARA and Daily Priorities\n04:37 Analog Cards vs Apps\n06:00 AI Surfacing Tasks\n08:45 Danger of False Productivity\n12:03 Parallelizing Bug Fixes\n13:24 Trust and Understanding Gaps\n16:34 Acceptance Tests Missing\n19:33 Back to Productivity Focus\n20:07 Obie Fernandez Prompt System\n21:11 Building the Command Center\n22:53 Daily Prompts to Slash Commands\n27:11 Minimalist Workflow and TickTick\n31:02 OpenClaw vs Safer Agents\n34:34 Finding the Right UI Layer\n37:07 Keeping AI in Its Place\n38:34 Wrap Up and Next Steps\n\nClaudeCode #Windsurf #AICoding #VSCode #CodingTools #AIProgramming","content_html":"\u003cp\u003eAfter 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.\u003c/p\u003e\n\n\u003cp\u003e\u003cstrong\u003eSponsor\u003c/strong\u003e\u003cbr\u003e\n\u003ca href=\"https://fireside.fm\" rel=\"nofollow noopener\"\u003eFireside\u003c/a\u003e\u003cbr\u003e\nPowerful podcast hosting \u0026amp; analytics\u003cbr\u003e\nBy podcasters, for podcasters. Since 2016\u003c/p\u003e\n\n\u003cp\u003e00:00 Back on the Mic\u003cbr\u003e\n00:45 AI Productivity Shift\u003cbr\u003e\n01:35 Email and Slack Triage\u003cbr\u003e\n03:43 PARA and Daily Priorities\u003cbr\u003e\n04:37 Analog Cards vs Apps\u003cbr\u003e\n06:00 AI Surfacing Tasks\u003cbr\u003e\n08:45 Danger of False Productivity\u003cbr\u003e\n12:03 Parallelizing Bug Fixes\u003cbr\u003e\n13:24 Trust and Understanding Gaps\u003cbr\u003e\n16:34 Acceptance Tests Missing\u003cbr\u003e\n19:33 Back to Productivity Focus\u003cbr\u003e\n20:07 Obie Fernandez Prompt System\u003cbr\u003e\n21:11 Building the Command Center\u003cbr\u003e\n22:53 Daily Prompts to Slash Commands\u003cbr\u003e\n27:11 Minimalist Workflow and TickTick\u003cbr\u003e\n31:02 OpenClaw vs Safer Agents\u003cbr\u003e\n34:34 Finding the Right UI Layer\u003cbr\u003e\n37:07 Keeping AI in Its Place\u003cbr\u003e\n38:34 Wrap Up and Next Steps\u003c/p\u003e\n\nClaudeCode #Windsurf #AICoding #VSCode #CodingTools #AIProgramming","summary":"We're back from hiatus to talk AI-driven productivity — how we each use AI tools to stay focused, running multiple Claude instances in parallel for bug fixes, and why integrated agent tools might beat the early open-source alternatives.","date_published":"2026-03-23T07:00:00.000-04:00","attachments":[{"url":"https://aphid.fireside.fm/d/1437767933/c8a4ad2b-dfe8-44f3-9a66-0f0713ee3407/cd30394e-07d8-4288-a2b1-c26b844ad52e.mp3","mime_type":"audio/mpeg","size_in_bytes":37439228,"duration_in_seconds":2339}]},{"id":"ba706e26-d908-4567-b4b0-a61621df8e48","title":"Episode 003: Claude Code vs Windsurf: Why I Switched AI Coding Tools","url":"https://vibing-with-ai-code.fireside.fm/003","content_text":"Thinking about switching AI coding tools? In this video, Baird breaks down his experience moving from Windsurf to Claude Code — why he made the switch, what each tool does well, and how they compare for real-world coding productivity. If you’re exploring AI coding assistants, VS Code extensions, or tools like Cursor, Claude, and Windsurf, this discussion will help you decide which is right for you.\n\nSponsor\nFireside\nPowerful podcast hosting \u0026amp; analytics\nBy podcasters, for podcasters. Since 2016\n\nClaudeCode #Windsurf #AICoding #VSCode #CodingTools #AIProgramming #ClaudeAI #Cursor","content_html":"\u003cp\u003eThinking about switching AI coding tools? In this video, Baird breaks down his experience moving from Windsurf to Claude Code — why he made the switch, what each tool does well, and how they compare for real-world coding productivity. If you’re exploring AI coding assistants, VS Code extensions, or tools like Cursor, Claude, and Windsurf, this discussion will help you decide which is right for you.\u003c/p\u003e\n\n\u003cp\u003e\u003cstrong\u003eSponsor\u003c/strong\u003e\u003cbr\u003e\n\u003ca href=\"https://fireside.fm\" rel=\"nofollow noopener\"\u003eFireside\u003c/a\u003e\u003cbr\u003e\nPowerful podcast hosting \u0026amp; analytics\u003cbr\u003e\nBy podcasters, for podcasters. Since 2016\u003c/p\u003e\n\nClaudeCode #Windsurf #AICoding #VSCode #CodingTools #AIProgramming #ClaudeAI #Cursor","summary":"Windsurf vs Claude Code — which AI coding tool actually delivers? Baird shares his firsthand switch and breaks down what each does best for real-world productivity. 🎙️ #ClaudeCode #Windsurf #AICoding #Cursor","date_published":"2026-03-15T05:00:00.000-04:00","attachments":[{"url":"https://aphid.fireside.fm/d/1437767933/c8a4ad2b-dfe8-44f3-9a66-0f0713ee3407/ba706e26-d908-4567-b4b0-a61621df8e48.mp3","mime_type":"audio/mpeg","size_in_bytes":29728686,"duration_in_seconds":1858}]},{"id":"56050201-ccd0-4a10-a421-4126b584b65b","title":"Episode 002: AI Keeps Forgetting? How to Manage Context in Coding Tools (Cursor, Claude, Windsurf)","url":"https://vibing-with-ai-code.fireside.fm/002","content_text":"Struggling with AI losing track of your prompts? In this episode, we dive into the context problem in AI coding—why large language models forget instructions, how it impacts developers, and practical strategies to manage context windows effectively.\n\nWe discuss:\n✅ How context retention affects AI coding in tools like Cursor, Windsurf, and Claude Code\n✅ Proven techniques for managing context in AI development\n✅ The future of AI interfaces, IDE integrations, and coding workflows\n✅ Insights on pricing shifts, new tools like Kira, and where AI coding is headed\n\nWhether you’re a software engineer, AI enthusiast, or just exploring the future of coding with AI, this conversation will help you understand how to keep your AI tools on track and get better results.\n\n👉 Listen now to level up your AI coding workflow and stay ahead of the curve!\n\nSponsor\nFireside\nPowerful podcast hosting \u0026amp; analytics\nBy podcasters, for podcasters. Since 2016\n\n\nBrendan's X/Twitter\n","content_html":"\u003cp\u003eStruggling with AI losing track of your prompts? In this episode, we dive into the context problem in AI coding—why large language models forget instructions, how it impacts developers, and practical strategies to manage context windows effectively.\u003c/p\u003e\n\n\u003cp\u003eWe discuss:\u003cbr\u003e\n✅ How context retention affects AI coding in tools like Cursor, Windsurf, and Claude Code\u003cbr\u003e\n✅ Proven techniques for managing context in AI development\u003cbr\u003e\n✅ The future of AI interfaces, IDE integrations, and coding workflows\u003cbr\u003e\n✅ Insights on pricing shifts, new tools like Kira, and where AI coding is headed\u003c/p\u003e\n\n\u003cp\u003eWhether you’re a software engineer, AI enthusiast, or just exploring the future of coding with AI, this conversation will help you understand how to keep your AI tools on track and get better results.\u003c/p\u003e\n\n\u003cp\u003e👉 Listen now to level up your AI coding workflow and stay ahead of the curve!\u003c/p\u003e\n\n\u003cp\u003e\u003cstrong\u003eSponsor\u003c/strong\u003e\u003cbr\u003e\n\u003ca href=\"https://fireside.fm\" rel=\"nofollow noopener\"\u003eFireside\u003c/a\u003e\u003cbr\u003e\nPowerful podcast hosting \u0026amp; analytics\u003cbr\u003e\nBy podcasters, for podcasters. Since 2016\u003c/p\u003e\n\n\u003cul\u003e\n\u003cli\u003e\u003cstrong\u003e\u003ca href=\"https://x.com/brendanwb\" rel=\"nofollow noopener\"\u003eBrendan's X/Twitter\u003c/a\u003e\u003c/strong\u003e\u003c/li\u003e\n\u003c/ul\u003e","summary":"AI keeps forgetting your prompts? 🚀 We discuss ways to manage context windows in tools like Cursor, Windsurf, and Claude Code, plus strategies to keep AI coding sharp, efficient, and on track","date_published":"2025-09-08T06:00:00.000-04:00","attachments":[{"url":"https://aphid.fireside.fm/d/1437767933/c8a4ad2b-dfe8-44f3-9a66-0f0713ee3407/56050201-ccd0-4a10-a421-4126b584b65b.mp3","mime_type":"audio/mpeg","size_in_bytes":25663664,"duration_in_seconds":1603}]},{"id":"23e1ec6d-970b-4ca7-b5e8-0fe6a65abaa8","title":"Episode 001: The Beginning","url":"https://vibing-with-ai-code.fireside.fm/001","content_text":"In this inaugural episode, brothers Brendan and Baird discuss their backgrounds as developers and share insights on AI-assisted coding. They delve into their experiences using AI tools like Cursor, Windsurf, and Claude, and explore topics such as AI coding workflows, the initial challenges of vibe coding, security concerns, and the long-term impact on coding skills. The episode also touches on innovative features in the AI world like Claude Swarm and AI-driven app development. Tune in to hear their candid thoughts and see how they navigate the evolving landscape of AI in software development.\n\n00:00 Introduction and Episode Overview\n00:38 Meet the Hosts: Brendan and Baird\n02:02 Exploring AI as a Coding Partner\n02:51 AI Coding Workflows and Experiences\n04:45 Challenges and Limitations of AI Coding\n23:50 Security Concerns in AI-Generated Code\n29:56 Future of AI in Coding and Final Thoughts\n33:14 Cool AI News and Wrap-Up\n\nLINKS\n\n\nClaude On Rails\n\n\nSponsor\nFireside\nPowerful podcast hosting \u0026amp; analytics\nBy podcasters, for podcasters. Since 2016\n\n\nBrendan's X/Twitter\n","content_html":"\u003cp\u003eIn this inaugural episode, brothers Brendan and Baird discuss their backgrounds as developers and share insights on AI-assisted coding. They delve into their experiences using AI tools like Cursor, Windsurf, and Claude, and explore topics such as AI coding workflows, the initial challenges of vibe coding, security concerns, and the long-term impact on coding skills. The episode also touches on innovative features in the AI world like Claude Swarm and AI-driven app development. Tune in to hear their candid thoughts and see how they navigate the evolving landscape of AI in software development.\u003c/p\u003e\n\n\u003cp\u003e00:00 Introduction and Episode Overview\u003cbr\u003e\n00:38 Meet the Hosts: Brendan and Baird\u003cbr\u003e\n02:02 Exploring AI as a Coding Partner\u003cbr\u003e\n02:51 AI Coding Workflows and Experiences\u003cbr\u003e\n04:45 Challenges and Limitations of AI Coding\u003cbr\u003e\n23:50 Security Concerns in AI-Generated Code\u003cbr\u003e\n29:56 Future of AI in Coding and Final Thoughts\u003cbr\u003e\n33:14 Cool AI News and Wrap-Up\u003c/p\u003e\n\n\u003cp\u003e\u003cstrong\u003eLINKS\u003c/strong\u003e\u003c/p\u003e\n\n\u003cul\u003e\n\u003cli\u003e\u003ca href=\"https://github.com/obie/claude-on-rails\" rel=\"nofollow noopener\"\u003eClaude On Rails\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\n\u003cp\u003e\u003cstrong\u003eSponsor\u003c/strong\u003e\u003cbr\u003e\n\u003ca href=\"https://fireside.fm\" rel=\"nofollow noopener\"\u003eFireside\u003c/a\u003e\u003cbr\u003e\nPowerful podcast hosting \u0026amp; analytics\u003cbr\u003e\nBy podcasters, for podcasters. Since 2016\u003c/p\u003e\n\n\u003cul\u003e\n\u003cli\u003e\u003cstrong\u003e\u003ca href=\"https://x.com/brendanwb\" rel=\"nofollow noopener\"\u003eBrendan's X/Twitter\u003c/a\u003e\u003c/strong\u003e\u003c/li\u003e\n\u003c/ul\u003e","summary":"In this inaugural episode, brothers Brendan and Baird discuss their backgrounds as developers and share insights on AI-assisted coding.  Tune in to hear their candid thoughts and see how they navigate the evolving landscape of AI in software development.","date_published":"2025-08-19T06:00:00.000-04:00","attachments":[{"url":"https://aphid.fireside.fm/d/1437767933/c8a4ad2b-dfe8-44f3-9a66-0f0713ee3407/23e1ec6d-970b-4ca7-b5e8-0fe6a65abaa8.mp3","mime_type":"audio/mpeg","size_in_bytes":35372807,"duration_in_seconds":2210}]}]}