For the previous decade and a half, I’ve been exploring the intersection of know-how, schooling, and design as a professor of cognitive science and design at UC San Diego. A few of you may need learn my latest 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 thousands and thousands of programming college students perceive how code executes. That have acquired me fascinated by 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 vital parts. However as these instruments have improved, I’ve discovered myself regularly letting go of the steering wheel in sure contexts. But I couldn’t totally 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 opinions. It’s a center path that’s labored surprisingly effectively for my private tasks, and as we speak I wish to share some insights from that journey.
Vibe Coding in Observe: Changing 250 HTML Information 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 sometimes 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 latest instance that completely illustrates this method. For a category I train, I had college students submit responses to a survey utilizing a proprietary internet app that offered an HTML export possibility. This left me with 250 HTML recordsdata containing beneficial pupil suggestions, nevertheless it was buried in a large number of pointless markup and styling code. What I actually wished 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.
Fairly than scripting this conversion script myself, I turned to Claude with a simple request: “Write me a Python script that converts these HTML recordsdata to Markdown, preserving textual content, fundamental formatting, and hyperlinks.” Claude urged utilizing the BeautifulSoup library (a strong selection) and generated an entire script that may course of all recordsdata in a listing, making a corresponding Markdown file for every HTML supply.
(On reflection, I noticed I most likely may 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 examine completely different approaches—you simply describe what you need and roll with what you get.)
True to the vibe coding philosophy, I didn’t evaluation the generated code line by line. I merely saved it as a Python file, ran it on my listing of 250 HTML recordsdata, 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 Threat 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 utterly unreviewed code on my precise laptop with actual knowledge. In conventional software program growth, this might be thought of reckless at finest. However the dynamics of belief really feel completely different with fashionable AI instruments like Claude 3.7 Sonnet, which has constructed up a repute for producing moderately protected and useful code.
My rationalization was partly primarily based on the script’s restricted scope. It was simply studying HTML recordsdata and creating new Markdown recordsdata alongside them—not deleting, modifying current recordsdata, or sending knowledge over the community. In fact, that’s assuming the code did precisely what I requested and nothing extra! I had no ensures that it didn’t embody some surprising habits 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 way more keen to vibe code with Claude or ChatGPT than I’d be with an unknown AI instrument from some obscure web site. These established instruments have reputations to keep up, and their guardian firms have sturdy incentives to forestall their programs from producing malicious code.
That mentioned, I’d like to see working programs develop a “restricted execution mode” particularly designed for vibe coding eventualities. Think about with the ability to specify: “Run this Python script, however solely enable it to CREATE new recordsdata on this particular listing, forestall it from overwriting current recordsdata, and block web entry.” This light-weight sandboxing would supply peace of thoughts with out sacrificing comfort. (I point out solely proscribing writes relatively than reads as a result of Python scripts sometimes must learn varied system recordsdata from throughout the filesystem, making learn restrictions impractical.)
Why not simply use VMs, containers, or cloud companies? As a result of for personal-scale tasks, the comfort of working immediately by myself machine is difficult to beat. Establishing Docker or importing 250 HTML recordsdata to some cloud service introduces friction that defeats the aim of fast, handy vibe coding. What I would like 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 supposed simply by inspecting the output. For my HTML-to-Markdown conversion, I may open up a number of of the ensuing Markdown recordsdata and see in the event that they contained the survey responses I anticipated. This guide spot-checking works moderately effectively for 250 recordsdata, 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 actually a less complicated script that verifies a fundamental property of the output out of your vibe-coded script. The important thing right here is that it needs to be a lot less complicated than the unique job, making it simpler to confirm its correctness.
For my HTML-to-Markdown conversion challenge, I noticed I may use a simple precept: Markdown recordsdata needs 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 recordsdata the place the conversion was incomplete! The unique script had didn’t correctly extract content material from sure HTML buildings. I took these problematic recordsdata, went again to Claude, and had it refine the unique conversion script to deal with these edge circumstances.
After a number of iterations of this suggestions loop—convert, examine, determine points, refine—I ultimately reached a degree the place there have been no extra suspiciously small Markdown recordsdata (effectively, there have been nonetheless a number of under 40%, however guide inspection confirmed these have been right conversions of HTML recordsdata with unusually excessive markup-to-content ratios).
Now you would possibly moderately ask: “In case you’re vibe coding the vibe examine script too, how are you aware that script is right?” Would you want a vibe examine on your vibe examine? After which a vibe examine for that examine? Effectively, fortunately, this recursive nightmare has a sensible answer. The vibe examine script is usually an order of magnitude less complicated than the unique job—in my case, simply evaluating file sizes relatively than parsing advanced HTML. This simplicity made it possible for me to manually evaluation and confirm the vibe examine code, even whereas avoiding reviewing the extra advanced authentic script.
In fact, my file measurement ratio examine isn’t good. It will probably’t inform me if the content material was transformed with the correct formatting or if all hyperlinks have been preserved accurately. Nevertheless it 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, at all times construct in vibe checks. Ask your self: “What less complicated script may confirm the correctness of my principal 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 velocity and inventive circulate of pure vibe coding and the reliability of extra rigorous software program growth methodologies. Consider vibe checks as light-weight assessments—not the great check 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 acceptable vibe checks routinely. Think about if Claude or related instruments couldn’t solely generate your requested script but in addition proactively provide: “Right here’s a easy verification script you would possibly wish to run afterward to make sure every little thing labored as anticipated.” I believe if I had particularly requested for this, Claude may have urged the file measurement comparability examine, however having this constructed into the system’s default habits can be extremely beneficial. I can envision specialised AI coding assistants that function in a semi-autonomous mode—writing code, producing acceptable checks, operating these checks, and involving you solely when human verification is actually wanted.
Mix this with the sort 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 forestall catastrophic errors.
And now for the meta twist: This complete weblog put up was itself the product of “vibe running a blog.” Firstly 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 research my writing type, tone, and typical construction—very similar to how a human collaborator would possibly learn my earlier work earlier than serving to me write one thing new.
As an alternative of writing all the put up in a single go, I broke it down into sections and offered Claude with an overview for every part separately. For each part, I included key factors I wished to cowl and generally particular phrasings or ideas to incorporate. Claude then expanded these outlines into totally shaped 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 wished to say and the way I wished to say it.
This iterative, section-by-section method mirrors the vibe coding methodology I’ve mentioned all through this put up. I didn’t want to write down each sentence myself, however I maintained management over the course, messaging, and closing approval. The AI dealt with the execution particulars primarily based on my high-level steerage, and I carried out verification checks at strategic factors relatively than micromanaging each phrase.
What’s notably fascinating is how this course of demonstrates the identical ideas of belief, verification, and iteration that I advocated for in vibe coding. I trusted Claude to generate content material in my type primarily based on my outlines, however I verified every part earlier than shifting to the subsequent. 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 totally seize his genuine voice, regardless of having his O’Reilly article as a reference. However in step with the vibe philosophy itself, he selected to not make investments extreme time in infinite refinements—accepting good-enough relatively than good.
Working section-by-section with out seeing the complete construction upfront created challenges, much like portray components of a mural with out seeing the entire design. I initially fell into the entice of copying his define verbatim relatively than reworking it correctly.
This collaboration highlights each the utility and limitations of AI-assisted content material creation. I can approximate writing types and increase outlines however nonetheless lack the lived expertise that provides human writing its genuine voice. The most effective outcomes got here when Philip offered clear course and suggestions.
The meta-example completely illustrates the core thesis: Generative AI works finest when paired with human steerage, discovering the proper 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 put up 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’d not have written it within the first place as a result of lack of time and power. I had sufficient power as we speak to stipulate some tough concepts, then let Claude do the “vibe running a blog” for me, however not sufficient to totally write, edit, and fret over the wording of a full 2,500-word weblog put up all on my own. Thus, identical to with vibe coding, one of many nice joys of “vibe-ing” is that it drastically lowers the activation power of getting began on artistic personal-scale prototypes and tinkering-style tasks. To me, that’s fairly inspiring.
