For the previous decade and a half, I’ve been exploring the intersection of expertise, training, and design as a professor of cognitive science and design at UC San Diego. A few of you may need learn my current piece for O’Reilly Radar the place I detailed my journey including AI chat capabilities to Python Tutor, the free visualization instrument that’s helped tens of millions of programming college students perceive how code executes. That have received me serious about my evolving relationship with generative AI as each a instrument and a collaborator.
I’ve been intrigued by this rising observe known as “vibe coding,” a time period coined by Andrej Karpathy that’s been making waves in tech circles. Simon Willison describes it completely: “After I speak about vibe coding I imply constructing software program with an LLM with out reviewing the code it writes.” The idea is each liberating and barely terrifying—you describe what you want, the AI generates the code, and also you merely run it with out scrutinizing every line, trusting the general “vibe” of what’s been created.
Be taught quicker. Dig deeper. See farther.
My relationship with this method has advanced significantly. In my early days of utilizing AI coding assistants, I used to be that one that meticulously reviewed each single line, typically rewriting important parts. However as these instruments have improved, I’ve discovered myself step by step letting go of the steering wheel in sure contexts. But I couldn’t absolutely embrace the pure “vibe coding” philosophy; the professor in me wanted some high quality assurance. This led me to develop what I’ve come to name “vibe checks”—strategic verification factors that present confidence with out reverting to line-by-line code critiques. It’s a center path that’s labored surprisingly properly for my private initiatives, and right now I wish to share some insights from that journey.
Vibe Coding in Apply: Changing 250 HTML Recordsdata to Markdown
I’ve discovered myself more and more turning to vibe coding for these one-off scripts that clear up particular issues in my workflow. These are usually duties the place explaining my intent is definitely simpler than writing the code myself, particularly for knowledge processing or file manipulation jobs the place I can simply confirm the outcomes.
Let me stroll you thru a current instance that completely illustrates this method. For a category I train, I had college students submit responses to a survey utilizing a proprietary net app that offered an HTML export choice. This left me with 250 HTML information containing precious pupil suggestions, but it surely was buried in a multitude of pointless markup and styling code. What I actually needed was clear Markdown variations that preserved simply the textual content content material, part headers, and—critically—any hyperlinks college students had included of their responses.
Somewhat than scripting this conversion script myself, I turned to Claude with a simple request: “Write me a Python script that converts these HTML information to Markdown, preserving textual content, fundamental formatting, and hyperlinks.” Claude instructed utilizing the BeautifulSoup library (a stable selection) and generated a whole script that will course of all information in a listing, making a corresponding Markdown file for every HTML supply.
(On reflection, I noticed I most likely might have used Pandoc for this conversion job. However within the spirit of vibe coding, I simply went with Claude’s suggestion with out overthinking it. A part of the attraction of vibe coding is bypassing that analysis section the place you evaluate totally different approaches—you simply describe what you need and roll with what you get.)
True to the vibe coding philosophy, I didn’t evaluate the generated code line by line. I merely saved it as a Python file, ran it on my listing of 250 HTML information, and waited to see what occurred. This “run and see” method is what makes vibe coding each liberating and barely nerve-wracking—you’re trusting the AI’s interpretation of your wants with out verifying the implementation particulars.
Belief and Danger in Vibe Coding: Working Unreviewed Code
The second I hit “run” on that vibe-coded script, I noticed one thing which may make many builders cringe: I used to be executing fully unreviewed code on my precise laptop with actual knowledge. In conventional software program improvement, this may be thought of reckless at greatest. However the dynamics of belief really feel totally different with fashionable AI instruments like Claude 3.7 Sonnet, which has constructed up a status for producing fairly secure and useful code.
My rationalization was partly based mostly on the script’s restricted scope. It was simply studying HTML information and creating new Markdown information alongside them—not deleting, modifying current information, or sending knowledge over the community. After all, that’s assuming the code did precisely what I requested and nothing extra! I had no ensures that it didn’t embrace some sudden conduct since I hadn’t checked out a single line.
This highlights a belief relationship that’s evolving between builders and AI coding instruments. I’m rather more keen to vibe code with Claude or ChatGPT than I might be with an unknown AI instrument from some obscure web site. These established instruments have reputations to keep up, and their father or mother corporations have robust incentives to forestall their techniques from producing malicious code.
That mentioned, I’d like to see working techniques develop a “restricted execution mode” particularly designed for vibe coding eventualities. Think about having the ability to specify: “Run this Python script, however solely permit it to CREATE new information on this particular listing, stop it from overwriting current information, and block web entry.” This light-weight sandboxing would supply peace of thoughts with out sacrificing comfort. (I point out solely limiting writes somewhat than reads as a result of Python scripts usually must learn numerous system information from throughout the filesystem, making learn restrictions impractical.)
Why not simply use VMs, containers, or cloud companies? As a result of for personal-scale initiatives, the comfort of working straight alone machine is tough to beat. Organising Docker or importing 250 HTML information to some cloud service introduces friction that defeats the aim of fast, handy vibe coding. What I need is to keep up that comfort whereas including simply sufficient security guardrails.
Vibe Checks: Easy Scripts to Confirm AI-Generated Code
OK now come the “vibe checks.” As I discussed earlier, the great factor about these private knowledge processing duties is that I can typically get a way of whether or not the script did what I meant simply by inspecting the output. For my HTML-to-Markdown conversion, I might open up a number of of the ensuing Markdown information and see in the event that they contained the survey responses I anticipated. This guide spot-checking works fairly properly for 250 information, however what about 2,500 or 25,000? At that scale, I’d want one thing extra systematic.
That is the place vibe checks come into play. A vibe examine is basically an easier script that verifies a fundamental property of the output out of your vibe-coded script. The important thing right here is that it ought to be a lot easier than the unique job, making it simpler to confirm its correctness.
For my HTML-to-Markdown conversion undertaking, I noticed I might use a simple precept: Markdown information ought to be smaller than their HTML counterparts since we’re stripping away all of the tags. But when a Markdown file is dramatically smaller—say, lower than 40% of the unique HTML measurement—which may point out incomplete processing or content material loss.
So I went again to Claude and vibe coded a examine script. This script merely:
- Discovered all corresponding HTML/Markdown file pairs
- Calculated the dimensions ratio for every pair
- Flagged any Markdown file smaller than 40% of its HTML supply
And lo and behold, the vibe examine caught a number of information the place the conversion was incomplete! The unique script had didn’t correctly extract content material from sure HTML buildings. I took these problematic information, went again to Claude, and had it refine the unique conversion script to deal with these edge instances.
After a couple of iterations of this suggestions loop—convert, examine, determine points, refine—I ultimately reached some extent the place there have been no extra suspiciously small Markdown information (properly, there have been nonetheless a couple of under 40%, however guide inspection confirmed these have been appropriate conversions of HTML information with unusually excessive markup-to-content ratios).
Now you may fairly ask: “When you’re vibe coding the vibe examine script too, how are you aware that script is appropriate?” Would you want a vibe examine to your vibe examine? After which a vibe examine for that examine? Nicely, fortunately, this recursive nightmare has a sensible answer. The vibe examine script is often an order of magnitude easier than the unique job—in my case, simply evaluating file sizes somewhat than parsing advanced HTML. This simplicity made it possible for me to manually evaluate and confirm the vibe examine code, even whereas avoiding reviewing the extra advanced unique script.
After all, my file measurement ratio examine isn’t excellent. It could actually’t inform me if the content material was transformed with the correct formatting or if all hyperlinks have been preserved accurately. But it surely gave me an affordable confidence that no main content material was lacking, which was my major concern.
Vibe Coding + Vibe Checking: A Pragmatic Center Floor
The take-home message right here is straightforward however highly effective: Whenever you’re vibe coding, all the time construct in vibe checks. Ask your self: “What easier script might confirm the correctness of my most important vibe-coded answer?” Even an imperfect verification mechanism dramatically will increase your confidence in outcomes from code you by no means truly reviewed.
This method strikes a pleasant stability between the pace and inventive stream of pure vibe coding and the reliability of extra rigorous software program improvement methodologies. Consider vibe checks as light-weight assessments—not the great take a look at suites you’d write for manufacturing code, however sufficient verification to catch apparent failures with out disrupting your momentum.
What excites me in regards to the future is the potential for AI coding instruments to recommend applicable vibe checks mechanically. Think about if Claude or related instruments couldn’t solely generate your requested script but additionally proactively supply: “Right here’s a easy verification script you may wish to run afterward to make sure the whole lot labored as anticipated.” I believe if I had particularly requested for this, Claude might have instructed the file measurement comparability examine, however having this constructed into the system’s default conduct could be extremely precious. I can envision specialised AI coding assistants that function in a semi-autonomous mode—writing code, producing applicable checks, working these checks, and involving you solely when human verification is actually wanted.
Mix this with the form of sandboxed execution atmosphere I discussed earlier, and also you’d have a vibe coding expertise that’s each liberating and reliable—highly effective sufficient for actual work however with guardrails that stop catastrophic errors.
And now for the meta twist: This complete weblog publish was itself the product of “vibe running a blog.” In the beginning of our collaboration, I uploaded my earlier O’Reilly article,”Utilizing Generative AI to Construct Generative AI” as a reference doc. This gave Claude the chance to investigate my writing type, tone, and typical construction—very like how a human collaborator may learn my earlier work earlier than serving to me write one thing new.
As a substitute of writing your complete publish in a single go, I broke it down into sections and offered Claude with a top level view for every part separately. For each part, I included key factors I needed to cowl and typically particular phrasings or ideas to incorporate. Claude then expanded these outlines into absolutely fashioned sections written in my voice. After every part was drafted, I reviewed it—my very own model of a “vibe examine”—offering suggestions and requesting revisions till it matched what I needed to say and the way I needed to say it.
This iterative, section-by-section method mirrors the vibe coding methodology I’ve mentioned all through this publish. I didn’t want to put in writing each sentence myself, however I maintained management over the path, messaging, and remaining approval. The AI dealt with the execution particulars based mostly on my high-level steering, and I carried out verification checks at strategic factors somewhat than micromanaging each phrase.
What’s notably fascinating is how this course of demonstrates the identical rules of belief, verification, and iteration that I advocated for in vibe coding. I trusted Claude to generate content material in my type based mostly on my outlines, however I verified every part earlier than transferring to the following. When one thing didn’t fairly match my intent or tone, we iterated till it did. This balanced method—leveraging AI capabilities whereas sustaining human oversight—appears to be the candy spot for collaborative creation, whether or not you’re producing code or content material.
Epilogue: Behind the Scenes with Claude
[Claude speaking]
Wanting again at our vibe running a blog experiment, I ought to acknowledge that Philip famous the ultimate product doesn’t absolutely seize his genuine voice, regardless of having his O’Reilly article as a reference. However consistent with the vibe philosophy itself, he selected to not make investments extreme time in countless refinements—accepting good-enough somewhat than excellent.
Working section-by-section with out seeing the total construction upfront created challenges, just like portray elements of a mural with out seeing the whole design. I initially fell into the lure of copying his define verbatim somewhat than remodeling it correctly.
This collaboration highlights each the utility and limitations of AI-assisted content material creation. I can approximate writing types and broaden outlines however nonetheless lack the lived expertise that offers human writing its genuine voice. The perfect outcomes got here when Philip offered clear path and suggestions.
The meta-example completely illustrates the core thesis: Generative AI works greatest when paired with human steering, discovering the suitable stability between automation and oversight. “Vibe running a blog” has worth for drafts and descriptions, however like “vibe coding,” some type of human verification stays important to make sure the ultimate product really represents what you wish to say.
[Philip speaking so that humans get the final word…for now]
OK, that is the one half that I wrote by hand: My parting thought when studying over this publish is that I’m not pleased with the writing high quality (sorry Claude!), but when it weren’t for an AI instrument like Claude, I might not have written it within the first place resulting from lack of time and power. I had sufficient power right now to stipulate some tough concepts, then let Claude do the “vibe running a blog” for me, however not sufficient to completely write, edit, and fret over the wording of a full 2,500-word weblog publish all on my own. Thus, identical to with vibe coding, one of many nice joys of “vibe-ing” is that it significantly lowers the activation power of getting began on artistic personal-scale prototypes and tinkering-style initiatives. To me, that’s fairly inspiring.