More On Vibecoding From Ethan Mollick
Then I thought about one of our most influential voices in today's tech world, MIT PhD Ethan Mollick, and I went over to his blog, One Useful Thing, to see if he was covering this new capability.
Sure enough, I found a March 11 piece titled 'Speaking Things Into Existence' where Mollick covers this idea of 'ex nihilo' code creation based on informal prompting.
In digging into this revolutionary use case, Mollick starts right up top with a quote from Karpathy that I think gets to the very heart of things – that 'the hottest new programming language is English.'
Presumably, you could use other world languages, too, but so much of what happens in this industry happens in English, and hundreds of thousands of seasoned professionals are getting used to the idea that you can talk to an LLM in your own language, not in Fortran or JavaScript or C-sharp, but just in plain English, and it will come up with what you want.
Mollick tells us how he 'decided to give it a try' using Anthropic's Claude Code agent.
'I needed AI help before I could even use Claude Code,' he said, citing the model's Linux build as something to get around. Here, Mollick coins the phrase 'vibetroubleshooting', and says 'if you haven't used AI for technical support, you should.'
'Time to vibecode,' Mollick wrote, noting that his first prompt to Claude Code was: 'make a 3-D game where I can place buildings of various designs, and then drive through the town I create.'
'Grammar and spelling issues included,' he disclaims, 'I got a working application about four minutes later.'
He then illustrates how he tweaked the game and solved some minor glitches, along with additional prompts like:
'Can you make buildings look more real? Can you add in a rival helicopter that is trying to extinguish fires before me?'
He then provides the actual cost for developing this new game – about $5.00 to make the game, and $8.00 to fix the bug.
'Vibecoding is most useful when you actually have some knowledge and don't have to rely on the AI alone,' he adds. 'A better programmer might have immediately recognized that the issue was related to asset loading or event handling. And this was a small project… This underscores how vibecoding isn't about eliminating expertise but redistributing it - from writing every line of code to knowing enough about systems to guide, troubleshoot, and evaluate. The challenge becomes identifying what 'minimum viable knowledge' is necessary to effectively collaborate with AI on various projects.'
'Expertise clearly still matters in a world of creating things with words,' Mollick continues. 'After all, you have to know what you want to create; be able to judge whether the results are good or bad; and give appropriate feedback.'
On the part of the machines, he refers to a 'jagged frontier' of capabilities.
That might be fair, but the idea that humans are there for process refinement and minor tweaking is sort of weak tea compared to the staggering capability of these machines to do the creative work. How long until model evolution turns that jagged edge into a spectacular smooth scalpel?
At the same time that we're trying to digest all of this, there's another contender in the ring. A bit later in the blog, Mollick references Manus, a new Chinese AI agent that uses Claude and other tools for fundamental task management.
Mollick details how he asked Manus to 'create an interactive course on elevator pitching using the best academic advice.'
'You can see the system set up a checklist of tasks and then go through them, doing web research before building the pages,' he says. 'As someone who teaches entrepreneurship, I would say that the output it created was surface-level impressive - it was an entire course that covered much of the basics of pitching, and without obvious errors! Yet, I also could instantly see that it was too text heavy and did not include opportunities for knowledge checks or interactive exercises.'
Here, you can see that the system is able to source the actual content, the ideas, and then arrange them and present them the right way. There's very little human intervention or work needed. That's the reality of it.
We just had the Chinese announcement of DeepSeek tanking stocks like Nvidia. What will Manus do? How does the geopolitical interplay of China and the U.S. factor into this new world of AI software development?
That question will be answered pretty soon, as these technologies make their way to market.
As for Mollick, he was also able to dig up old spreadsheets and get new results with the data-crunching power of AI.
'Work is changing, and we're only beginning to understand how,' Mollick writes. 'What's clear from these experiments is that the relationship between human expertise and AI capabilities isn't fixed. …
The current moment feels transitional. These tools aren't yet reliable enough to work completely autonomously, but they're capable enough to dramatically amplify what we can accomplish.'
There's a lot more in the blog post – you should read the whole thing, and think about the work processes that Mollick details. On a side note, I liked this response from a poster named 'Kevin' that talks about the application to teams culture:
'To me, vibecoding is similar to being a tech lead for a bunch of junior engineers,' Kevin writes. 'You spend most of your time reviewing code, rather than writing code. The code you review is worse in most ways than the code you write. But it's a lot faster to work together as a team, because the junior engineers can crank through a lot of features. And your review really is important - if you blindly accept everything they do, you'll end up in trouble.'
Taking this all in, in the context of what I've already been writing about this week, it seems like many of the unanswered questions have to do with human roles and positions. Everything that we used to take for granted is changing suddenly. How are we going to navigate this? Can we change course quickly enough to leverage the power of AI without becoming swamped in its encompassing power?
Feel free to comment, and keep an eye on the blog as we head toward some major events in the MIT community this spring that will have more bearing on what we're doing with new models and hardware setups.
Hashtags
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
Yahoo
10 hours ago
- Yahoo
MIT Student Drops Out Because She Says AGI Will Kill Everyone Before She Can Graduate
We're all probably feeling a little anxious about AI. It's horrible for the environment, is used as an excuse to fire workers, floods the internet with misinformation and slop, entrenches government surveillance, and appears to be driving people into psychosis. And so, at a time when many college students are dropping out to join AI startups, one former MIT student says she called it quits because she's afraid of something altogether more catastrophic: that an artificial general intelligence (AGI), or superhuman AI, will completely wipe out the human race, Forbes reports. "I was concerned I might not be alive to graduate because of AGI," Alice Blair, who enrolled at the university in 2023, told the publication. "I think in a large majority of the scenarios, because of the way we are working towards AGI, we get human extinction." Blair now works as a technical writer at the nonprofit Center for AI Safety, and has no plans to go back to MIT. She joined, hoping to meet other people interested in making AI safe, and apparently was disappointed. "I predict that my future lies out in the real world," she told Forbes. Nikola Jurković, a Harvard alum who served at his school's AI safety club, is sympathetic to the idea. "If your career is about to be automated by the end of the decade, then every year spent in college is one year subtracted from your short career," he told Forbes. "I personally think AGI is maybe four years away and full automation of the economy is maybe five or six years away." Building an AGI, a system that matches or surpasses human intelligence, is much of the AI industry's endgame. OpenAI CEO Sam Altman called the recent launch of its poorly-received AI model GPT-5 a major stepping stone towards AGI, even going as far as to call it "generally intelligent." Many experts are skeptical, however, that we're anywhere near building such a powerful AI model, and point to recent signs that improvements to the tech are hitting a wall. "It is extremely unlikely that AGI will come in the next five years," Gary Marcus, an AI researcher and outspoken critic of the industry, told Forbes. "It's just marketing hype to pretend otherwise when so many core problems (like hallucinations and reasoning errors) remain unsolved." And while there are very real forms of harm that AI can cause, outright extinction is a little far-fetched, Marcus said. In fact, the AI industry probably wants you to buy into AI doomsday prophesying. Altman and other tech CEOs raise these risks themselves. Doing so creates the impression that the tech is far more capable than it currently is, and allows these companies to control the narrative around how the tech should be regulated. And if you're envisioning an apocalypse like in "The Matrix" movies — human enslavement at the hands of machine intelligences that rebelled against their creators — you may be ignoring the very mundane forms of harm it's already causing, like job automation and the gutting of the environment. More on AI: Sam Altman Calls His Own AI Model "Annoying" After Being Forced to Raise It From the Dead Solve the daily Crossword
Boston Globe
13 hours ago
- Boston Globe
The docuseries ‘Built in Birmingham: Brady & the Blues' isn't bad, except the Tom Brady parts
Well, here's the basic timeline. Appreciated every extraordinary thing he did on the field during his 20 years with the Patriots … recognized he was getting weird on us with stuff like the Alex Guerrero connection, offensively overpriced TB12 gear, and the no-mushroom policy, but hey, his unprecedented late-career excellence made for a heck of a case on his behalf … cringed when the formerly down-to-earth young QB who used to chug beers faster than his linemen started pushing crypto and running with the oligarch class… watched almost every broadcast of his rookie season as Fox's lead NFL analyst last fall, eventually concluding that the reason he didn't show much personality is that it might not be there to show … But the tipping point that brought on the aforementioned realization was Brady's behavior in his version of a current trend among the rich, famous, and presumably bored — buying an English soccer team, and making a documentary about it in which the star is the rescuing hero. Advertisement 'Built in Birmingham: Brady & the Blues' is a five-episode docuseries that debuted at the end of July on Amazon Prime. It's about a Champions League soccer team (the second tier in English soccer, below the Premier League) that Brady and his private equity pal Tom Wagner recognize as an undervalued asset (always heart-warming when vultures find their food) and purchase, with Brady taking on minority ownership but with full boss duties. Advertisement 'Built in Birmingham' is not bad at all. The city (gritty, industrial, and full of amusingly blunt fans that will remind you of specific Ted Lasso side characters), players (the third episode, featuring star player Jay Stansfield's back story, is the best in the series), and the team (whose history roughly resembles the Red Sox' from 1919-2003) are compelling. The problem is it's far less interesting when Brady is around. He speaks to the players in bromides and banalities — 'We practice like it's the Super Bowl' — about his time with the Patriots (and Bucs), which he seems to presume these futbol players know from A to Z and XXXVI to LV. He punctuates his Cliff Notes Tony Robbins proclamations with a specific expletive so often that it's a wonder it hasn't slipped through on a Fox broadcast. Related : When he is involved, Brady — who describes his role as 'being there in a visionary role' — only seems authentic when he's belittling something or angry. He joins his friends in talking condescendingly about the city and the team as they're on he way to see the Blues' aged facilities for the first time. Before a game against Wrexham — famously owned by actors Ryan Reynolds and Rob McElhenney — Brady tells the camera, 'Let's go get a [expletive] win against Wrexham ... Ryan Reynolds, Mackilrey, whatever your [expletive] name is.' Advertisement When Wagner informs Brady that putting together a swag bag for visiting legend David Beckham would be considered a faux pas — Beckham never played for the team — Brady gets a look on his face that suggests Joey Galloway just ran the wrong route again. He tells Wagner through a scowl that Beckham should be gifted something anyway. He likes to talk about how he was an underdog, but he comes across as someone who can no longer remember what that was like, or what he was like. The most off-putting scene occurred in the opening episode when Brady, Wagner, and his team strategized in the back of an SUV before popping into a local pub to meet some fans for a quick public-relations opportunity and a few more Lasso vibes. 'We have to feel this one out, boys,'' Brady says. 'This is not my thing.' He's told it will only be 15 minutes. He asks if he'll be signing autographs. The pop-in is designed to make him look like a man of the people. He's friendly enough once he's in the pub, but we know how he really feels. His people these days aren't the ones chugging beers. I was hoping while watching the series that Brady might have a revelation by the fifth episode, ditch the processed corporate speak, abandon the arrogant expectation that whatever he says carries weight because of what he accomplished in the NFL, and show some authentic emotion, like he did after winning those first few Super Bowls. I was hoping any success he found in Birmingham would remind him of his best times with the Patriots, and thereby bring out genuine emotions. Related : Advertisement Instead, that happened with, of all people, Wagner, the calculating investor, who by the end is fully invested in the people on this team. I won't spoil the circumstances, because this show is worth watching, despite the Brady frustrations. In the fifth episode, Wagner makes a truly stirring and heartfelt speech, and as I was watching it, I couldn't help but think, 'Man, when the private-equity guy can summon more passion than Tom Brady, that's awfully damning.' Hmmm. Maybe Fox should give Wagner a shot as its lead NFL analyst. Tom Brady comes back to Gillette Stadium for the unveiling of this statue before the New England Patriots preseason game versus the Washington Commanders. Chad Finn can be reached at
Los Angeles Times
13 hours ago
- Los Angeles Times
Combine Pedro Almodóvar with stop-motion and you get Adult Swim's most unexpected yet perfect show
In the annals of things I could not have seen coming, none has been more unexpected than 'Women Wearing Shoulder Pads,' a queer Spanish-language stop-motion comedy melodrama, set in the aesthetic world of a 1980s Pedro Almodóvar film. (It arrives Sunday at midnight on Adult Swim, the home of things one doesn't see coming, and premieres the next day on HBO Max.) Though it takes place in Ecuador, its central character, Marioneta Negocios (Pepa Pallarés), is Spanish, and it's easy enough to imagine Almodóvar muse Carmen Maura in the role — though it is also impossible to imagine the story told as well, or at all, in any other way. When I call this series perfect, notwithstanding the happy imperfections of its puppets and sets, it's not because everything works as its meant to, but because there's nothing you can measure it against — it occupies its own self-created space. Every element is necessary. Even presenting it in English would be to lose romantic, dramatic, telenovelistic force. At the center of the story is the cuy, a guinea pig eaten in Andean South America, though in this telling they're also used in a version of bullfighting. (Some cuys are large enough to ride on.) The primary action is a power struggle between Marioneta, a socialite running a campaign promoting cuy as pets, not food, and Doña Quispe (Laura Torres), who has risen from life as a humble butcher to the anything-but-humble CEO of the country's most famous restaurant, El Cuchillo (the knife). Mixed up in their lives are Coquita Buenasuerte (Gabriela Cartol), Marioneta's seemingly happy-go-lucky assistant; Espada Muleta (Kerygma Flores), a matadora in love with Marioneta; Nina (Nicole Vazquez), Doña Quispe's vegetarian daughter, serving a pro-cuy group as its Minister of Refreshments and Head of Recruitment for Rebellious Teens — 'I have looked upon the caged cuy through the prison of capitalist enterprise, through the hubristic iron bars of a homocentric world view' — who will become a pawn in the older women's game. Not everything will be as it seems. Created by Gonzalo Cordova (a veteran of 'Tuca & Bertie' and 'Adam Ruins Everything') and produced by the Mexican animation studio Cinema Fantasma, the series comes packaged as eight 11-minute episodes — that is cartoon length — which neatly constitute a short feature film. On the bill are mystery, suspense, terror, revenge, hot romance (including some puppet sex), masked stalkers, performance art, love notes posted with knives, parodies of television shows and commercials, old secrets coming to light and nuns singing karaoke. From 'Gumby' to 'Rudolph' to 'Wallace and Gromit' to 'The Fantastic Mr. Fox,' stop motion is of all forms of animation most magical and in its real-space, three dimensional, handcrafted way the most like life, if not necessarily the most lifelike. (It can look ungainly, which is also part of its charm.) It's a magnification of childhood playtime, a puppet show in which the puppets have broken loose from the puppeteers. The cleverness of the execution is as or more important than how seamless it is. 'Women Wearing Shoulder Pads' does all sorts of neat tricks, some you notice and more you simply accept — and when deemed necessary, or just amusing, it will insert a live-action hand or mouth. It's an exaggerated world — appropriately to the heavy-breathing material — but emotionally expressive, even moving, and lots of fun.
