Three consumer boxes claim they can run DeepSeek V4 Flash for a two-Hermes homelab: NVIDIA’s DGX Spark, Apple’s Mac Studio, and AMD’s Ryzen AI Max+ 395. Only two of them can reach the memory tier the model needs to run lossless.
A new local model gets validated by a dashboard feature built before it existed. A DNS outage traces back to two unrelated bugs. A deliberate reboot of the homelab’s Proxmox host finds a third bug neither fix would have caught.
A phone-friendly status page for a two-machine homelab, built in phases. Why it lives on the Proxmox box next to Home Assistant instead of the AI workstation, how it talks to Uptime Kuma with no REST API to speak of, and why the third phase, waking the workstation remotely, is still waiting on a cable move.
Four tables disappeared without a trace on the Substack mirror of a recent post — not a bug in this site’s pipeline, but a platform limitation with a fix worth building anyway. Then a full, risk-sorted update pass across every tool the homelab runs on, including an NVIDIA driver near-miss and a Home Assistant instance retired for real this time. Closes with a one-character YAML fix that had taken down the entire site’s production build.
A full census of every tag on 82 posts found 47 of them, a third used exactly once, fixed with a scripted consolidation down to 21. Then a three-week streak of silent GitHub Actions failures traced back to one expired token nobody noticed rotate out.
A full feature build inside an existing vibe-coded app, start to finish: a plan-first conversation, two shipped phases, a progression system, two new MCP tools, and a glossary page that only exists because testing surfaced a gap the code itself never needed to close. Less about dumbbells, more about what it actually looks like to build something substantial into an app that already works.
One extended session on my personal fitness tracker turned up three real bugs, not one. A Tonal sync that silently died 14 hours out of every 24 because of an Auth0 token-lifetime mismatch, found by pulling live production logs instead of guessing. A years-old duplicate-workout bug that survived a prior “fix” because the matching logic was too strict, plus a self-inflicted unique-constraint bug I caught testing against production before it ever shipped. And a cleanup pass that found a second real bug hiding in plain sight, one repo review away.
Knowledge workers have been vibe coding for decades — it was just called VBA. That history has a second lesson buried in it: the technically better spreadsheet lost the 1980s, and the one with distribution won. Claude Code is winning on quality the way Lotus 1-2-3 did. Copilot is betting that doesn’t matter, and this time Microsoft isn’t just waiting around for the product to catch up.
My gaming rig’s Windows partition used to cost me 15-45 minutes of manual clicking every time I booted into it. One afternoon: a Coder workspace talking to it over Tailscale and SSH, an inventory script that catalogs every update channel on the machine, three Scheduled Tasks that actually do the work, a toast notification bug that took longer to fix than the automation itself, and a Next.js dashboard on Vercel to see it all without ever touching the machine.
115 days after building this blog from a cabana in Cabo, I spent one afternoon — 2:54 PM to 6:23 PM, back to back — running a chain of admin panel improvements: image upload, a visual TODO viewer, drag-and-drop reorder, a “launch agent” button, four rounds of troubleshooting it, and three mobile layout bugs found by actually using it on my phone at the end.
I kept typing the same paragraph into Coder Agents chat every time a session ran long or I needed to SSH into the homelab. A Slack conversation with a colleague turned that annoyance into five reusable slash commands — and along the way I discovered Coder Agents actually has two entirely separate skill systems, only one of which the `/` menu will ever show you.
My Windows gaming rig, hostname Stormtrooper, had a case fan installed backwards. Turning it around dropped GPU temps 16-18°C. Then I went looking for a CPU undervolt and found out the board doesn’t have one. Then I tried to make idle quieter and accidentally cooked the CPU 18°C hotter across every phase, including the ones with no load at all. Four thermal test runs, one Core Ultra 9 285K, and a lot of honest data.
A weekly homelab housekeeping pass (Ollama out, Home Assistant current, RustDesk re-pulled), a quote-marks bug that turned out to be a content pipeline gap rather than a font problem, and a full audit of this blog’s own “By the Numbers” habit that found it wasn’t as consistent as assumed.
A senior architect at a financial services firm told me chat context is now more valuable than code. It turns out a whole ecosystem — an arXiv paper with seven interoperable language implementations, two “Git for memory” projects, and zero agreement across model providers — is already racing to answer his question.
Sometimes your agent’s turn just ends with no result — no error, no output, nothing. Nudging it usually gets you the answer that was there the whole time. It’s tempting to write that off as a UX hiccup. Sometimes it’s a real bug, and finding out is part of the fun of vibe coding. A walkthrough of why that’s worth investigating, when it crosses the line into “file this,” and how to do it well — using a hanging GitHub tool call as the live example.
My wife saw OpenAI’s new Codex Micro and thought she could skip buying one — she already has a Stream Deck. That sent me down a rabbit hole: what the device actually does, how it compares to the Elgato hardware it’s built on top of, and whether a Linux homelab version is a real project or just another case of reinventing a wheel. A survey first, a build plan second, no results yet.
A follow-up research sprint to the rainy-day tool scouting post, this time chasing down a word instead of a stack: where “alpha” actually comes from, why the All-In podcast keeps warning enterprises not to hand theirs to a frontier lab, and what the frontier-vs-self-hosted tradeoff looks like when you shrink it down to homelab scale.
What started as a Thursday Thoughts hot take on the OpenAI/Hugging Face eval-sandbox breach turned into a research sprint: a survey of existing AI agent containment standards, a deep look at the closest one we found (the Agent Sandbox Taxonomy), an attempt to score the actual incident against it using nothing but public disclosures, and a plan to validate then run Coder itself through the assessment.
Six months of running a side project with AI agents convinced Rob Whiteley that the real dividing line in the AI era isn’t technical background or access to tools. It’s curiosity, and that reframes who actually gets left behind.
A challenge to a coding agent: prove whether months of homegrown test harnesses and bakeoff scripts were reinventing wheels that already exist. A survey of what hobbyists, techtubers, and the AI benchmarking industry already publish, and an honest verdict on this blog’s own tooling habits.
The May audit closed clean. Since then we shipped an MCP server, a Slack integration, and a shareable-snippet image generator -- three new pieces of attack surface that postdated every finding in that audit. A fresh scan against the same categories found 8 issues across the old surface and the new. Three phases, three commits, about an hour, one repo.
Building an app across dozens of disconnected agent sessions accumulates bugs. That’s the tax on staying hyper-vigilant across two axes at once: does it work the way a person experiences it, and does it hold up against someone trying to break it. This week split cleanly into both. Here are the four small bugs, each hiding in a corner some check didn’t cover. Monday’s post covers the security axis.
I put Qwen 3.6 27B, Qwen 3.6 35B-A3B, Qwythos-9B, GLM-4.7-Flash, and Nemotron-3-Nano through the same real coding task on my homelab RTX 5090. Along the way I had to live-patch two separate llama.cpp bugs — and even after fixing them, I couldn’t fully prove one model’s failure wasn’t the harness’s fault.
Back in Q1 I read a headline about Google cutting AI memory use 6x and filed it under “watch and revisit.” Four months later, Google still hasn’t shipped official code, but a whole ecosystem of forks has, llama.cpp has an open PR, and at least one compatibility gotcha lands squarely on our daily driver. Here’s the honest state of TurboQuant heading into Q3, and the test I’d actually run against it.
Anthropic and AWS are both, underneath everything else, infrastructure providers renting out specialized compute. But the sharper parallel is behavioral — both built a thriving ecosystem, then started eating pieces of it. Claude Design blindsiding Figma and Canva looks a lot like AWS’s Elasticsearch moment, except it’s happening at a pace AWS never approached, and one layer higher up the stack.
Mid-research on the LocalAI bakeoff, I got asked a blunt question: why not just run Coder Agents as the homelab supervisor too? The answer split my original coding-vs-general-purpose hypothesis into a sharper dichotomy — ephemeral/invoke-driven/git-centric vs. persistent/event-driven/tool-centric — and pointed straight at Turnstone as the next thing worth a real bakeoff.
A gloomy Cape Cod afternoon post-July 4th turns into a deep dive on ComfyUI, Lemonade Server, and LocalAI — plus llama-benchy and AMD’s AI Playbooks — and the case for a bakeoff against our hand-tuned llama.cpp stack.
A personal gaming-settings tracker built end-to-end with an agent: 28 curated profiles, a JSON API, an MCP server, and a dropdown that quietly pointed at data that didn’t exist. Five lessons from building it solo.
GLM is suddenly everywhere in developer conversations. Before we run the bakeoff, we need to answer two questions: what is GLM, and is it suitable for a single RTX 5090 homelab?
A full-tower AI homelab with a 420mm AIO gets rebuilt into an SFF open-frame case with custom hardline water cooling. Two 240mm slim radiators, a single shared loop, 580W peak heat load, and 2,726 sensor readings that prove whether the tradeoff was worth it.
Three bugs that looked fixed from the wrong vantage point. An unquoted YAML date that crashed the public homepage one month after we wrote a blog post about the same bug. A model string that worked until its deprecation date passed. A security commit that stacked three invisible failures on top of each other. And a lesson about what accumulates when you build fast with agents.
A finance intern is spending her summer observing business processes and vibe coding automation tools. Not a CS major. Not shadowing someone. Building something real. It is a small example that says something big about how AI is reshaping internships, careers, and what the word “developer” actually means.
Vibe coding has moved from hobbyist curiosity to enterprise rollout across knowledge workers, and the next wave of AI adoption will be defined by governance and token economics.
A CEO panel at an AI event sparked a simple but powerful question every startup founder should ask themselves: does your business get better as AI models improve, or does it get worse?
I gave five local LLMs and one frontier cloud model the same coding task on my homelab: build a tag manager for the blog’s admin panel. Only two shipped anything. Here’s what happened.
Four frontier models, ten tasks, one government shutdown. We ran Claude Fable 5 through the homelab benchmark harness three hours before Anthropic pulled the plug — and it came in second. Here’s the full bakeoff.
Two Discord bots, one 14B model, five fitness-tracker tasks. Both agents failed on the first try. Getting them working required debugging context overflow, silent tool parameter drops, and a chat template flag that changes everything. The results reveal as much about the state of local AI agents as they do about which framework won.
Coder 2.34 shipped User Secrets — per-user credential storage that injects into every workspace automatically. We upgraded, audited 29 secrets across four projects, and found exactly two that belonged there. Here’s how we decided, how we migrated, and what we cleaned up along the way.
A model refresh on the homelab (Qwen 3.6, new embeddings, 469 llama.cpp builds), a feature sprint on the vacation planning site (calendar sync, expense tracking, and three bugs that taught us more than the features did), and automating Substack syndication after discovering two more undocumented quirks. Three unrelated workstreams, one theme: maintenance is where the real learning happens.
At a C-suite roundtable in Palo Alto last week, ten-plus executives from a mix of gaming platforms, enterprise systems providers, job sites, and other Bay Area titans landed on the same analogy without being prompted: we’ve seen this before. The lift-and-shift era of AI is already here. The native era — where you redesign workflows from scratch for agents, not humans — is what comes next.
I’ve been running OpenClaw on the homelab for a month. A recommendation sent me down the Hermes Agent rabbit hole — and the research before the first real test revealed my daily driver model was broken for tool calling all along.
Substack supports RSS import, but the importer is finicky, undocumented, and rejects feeds for reasons it won’t tell you. Here’s how we got 13 curated posts from a Next.js blog into Substack — and what every other guide leaves out, including the dedup gotcha that bit us on the re-import.
The fitness tracker MCP server was a test run. This week I added the same thing to vibescoder.dev — 16 tools that let any agent list posts, publish drafts, check analytics, trigger deploys, cross-post to Dev.to, and troubleshoot the live site. Here’s the build, the architectural decisions, and what it’s like when the agent that built the feature can immediately use it.
I asked an agent to security-audit my fitness tracker after wiring MCP into it. It found nineteen things. I fixed them all in four neat batches. Then the dashboard went empty, Google sign-in died, and the real bugs turned out to be the ones the audit couldn’t see — a middleware file that had been silently doing nothing for months, and an OAuth client that never existed in any project I owned.
One missing pair of quotes in one frontmatter field took down the admin drafts page. YAML 1.1 auto-parsed the date to a JS Date object, formatDate called .includes on it, and the route 500’d. Here’s the bisect from a mobile screenshot to a one-line fix, why only the drafts page broke, and the lesson about trusting types at the YAML boundary. Part two of a two-part Friday Fixes — see #1 for the scheduled-publish workflow bugs that landed the same day.
The scheduled-publish GitHub Action broke twice in nine days. Bug one: a grep that matched body text instead of frontmatter, triggered by a post about the feature itself. Bug two: a dead-code line introduced by the fix for bug one — racy under set -euo pipefail, probabilistically silent for eight days, then 42 consecutive failures with zero notifications.
Someone vibe coded an app with Google AI Studio. The Gemini API key shipped in the client-side JavaScript bundle. Google suspended the project. Here’s why every AI coding tool gets this wrong, why regular audits are the only real defense, and what you can do before it happens to you.
The Round 5 bakeoff produced four implementations. None of them shipped. What shipped was a merge of the best pieces from all four, then a polish pass against real data. Bakeoff → Merge → Polish is a generalizable pattern for any feature where the design space is genuinely unclear.
Three AI agents audited the blog and produced three different reports. Closing them out was its own job — triage, phasing, verification, and ten commits across two repos with zero build failures. Here’s the remediation arc, what shipped, what got deferred, and what the process revealed about working through someone else’s audit.
Our AEO audit gave vibescoder.dev a clean bill of health. Cloudflare’s isitagentready.com gave it a 25 out of 100. Both audits were right — they were measuring two different competencies. Here’s the side-by-side, what each one caught, and the two genuine gaps we shipped fixes for — taking the score from 25 to 33 (and on track for 39 after the next scan).
DeepSeek V4-Pro, V4-Flash, and Zyphra ZAYA1 are three of the most exciting new models in local AI. None of them run on our RTX 5090 homelab — for completely different reasons. Here’s the research, the math, and what it means for anyone building a local inference rig.
A second user joined the homelab Coder instance and couldn’t push to GitHub. What looked like a missing config turned into five chained problems, a domain migration aftershock, an agent-debugging-an-agent meta-moment, and the discovery that the same credential helper bug had been “fixed” four times in ten days — and never actually deployed.
Two AI models got the same prompt: review the blog fodder, check for redundancy, and draft a post. Opus chose a debugging war story. Qwen chose a data-driven redesign. Neither picked the same fodder. Here’s what the difference reveals about how models think about content.
Three rounds of iPhone screenshots to fix spacing that should have been right the first time. The fix wasn’t smaller padding — it was teaching the agent the pixel math once so it never forgets. Plus: admin pillbox for drafts, hamburger menu shortcut, Invalid Date bugs, and scheduled publishing for every draft.
As AI agents make code generation trivial, the real value shifts from storing source code to preserving the chat conversations that created it.
I asked an AI agent to turn off my RGB lights on Linux. 85 terminal commands, 35 failures, 4 hangs, 2 dead download links, one wrong build system, and the GPU is still glowing. This is the post.
A CRLF bug silently broke every workspace for weeks. Then we fixed it, taught the agent to remember, moved templates to Git, squashed a nested heredoc, cut boot time from 91 seconds to 5, automated the screenshot pipeline, and built scheduled publishing — which this post used to publish itself. Ten fixes, one week.
How AI agents are transforming software development the same way Google Maps revolutionized travel - making the impossible feel effortless and opening up new worlds of exploration.