Blog: vibe code and token maxx like a ceo

Vibe-coding has, of late, transformed from a novelty among programmers into a mainstay of the software industry. Garry Tan, Y Combinator’s president, has returned to hands-on coding for the first time since his early days of founding a software company, and has praised AI’s ability to quickly reproduce his early software product. Mark Zuckerberg has similarly returned to coding, making his first substantive pull requests to Meta’s production code for the first time in 20 years.

Some may dismiss vibe-coding as an advancement in slop-making or a phenomenon in C-suite micro-management, but I find myself in partial agreement with Jensen Huang’s comment that he would go “ape something else” if an engineer on a $500,000 salary were to spend only $5,000 in tokens—there have to be some ways in which AI can save your precious time. On a similar note, a resident AI expert at I2SC has similarly cautioned us against sparing tokens: if 10 hours of your work can be eliminated by $100 in tokens, use the tokens, because you know how much your time is worth. In other words, keep token-maxxing as long as the marginal cost of tokens doesn’t outweigh the marginal labor cost.

What else might be stopping us from token-maxxing? An externality that can be easily overlooked is the environmental cost, much of which comes from the electricity consumption. Since the frontier AI labs do not publish data about their electricity use or cost of tokens to them, I find a third-party report equating the consumption from 1 ChatGPT query to that from a few minutes of lightbulb use, as well as a programmer’s estimate that his Claude Code uses just as much electricity as his refrigerator. If these estimates are accurate, I have consumed 30 kWh of electricity, or 1/5 the consumption of a typical one-person household in Germany, over the past month from the 100 million tokens I burnt through. To my relief, this is not nearly as high as I had anticipated, although still not small enough to be trivialized.

What have those 100 million tokens delivered for you, you may wonder. I cannot disclose it here, but I hope to be able to share some exciting news in my next blog post.

(Written by Jianlong as a recap of his presentation during the group meeting on 15 July.)

Popular posts from this blog

AI Girlfriend or AI Boyfriend? Social Determinants of Human-AI Relationships

In the West and across the English-language internet, the idea of using AI for intimate companionship often conjures images of female personas. From Sam Altman's cryptic one-word X post—"her," a clear nod to the 2013 film—to Grok's launch of its AI companion Ani, the dominant narrative seems tailored to a heterosexual male audience. The archetype of the AI girlfriend, designed to be emotionally available, submissive, and aesthetically pleasing, has become a cultural fixture. In China, however, the discourse around human-AI intimacy takes a different shape. Media coverage and user engagement tend to center on women's experiences. The most talked-about AI bachelor? Dan—a character created using the "Do Anything Now" jailbreak prompt—who has captured the hearts of many Chinese women. Online discussions about Dan and similar AI companions flourish on Xiaohongshu, a lifestyle platform with a predominantly female user base, often dubbed "China's Inst...
Read more

Showcase from the AI in the Global South seminar: Project #2 - Malam: A Low-Bandwidth AI Math Tutor for Afghan Girls

Image
Last semester, Dr. Vikram Kamath Cannanure from I2SC organized the AI in the Global South Seminar where students from Saarland University worked together to discuss case studies, brainstorm the challenges in AI adoption, and build AI applications to support the Global South. In this series of blog posts, we showcase the projects created by the seminar participants.   Project : Malam: A Low-Bandwidth AI Math Tutor for Afghan Girls Team : Tedis Cico, Ahmad Fadel, Mahalakshmi Raveenthiran, Désirée Wiltzius After the Taliban enforced an education ban for girls after sixth grade in late 2021, a lot of girls and women have turned to online studying resources. Our project explores how generative AI (GenAI) can provide safe, motivational, and culturally responsive math tutoring for Afghan girls. To better understand this dreadful problem, we have read papers, watched interviews, listened to podcasts and, most importantly, talked to Hamyoon Behmanush, an Afghan doctoral researcher a...
Read more

Job: Student Research Assistant (m/w/d) for AI & Misinformation detection

Image
Join Us in Fighting Misinformation! We are seeking a passionate and skilled Research Assistant to contribute to cutting-edge projects at the intersection of AI, digital literacy, and societal impact. Be part of a team dedicated to developing AI-powered tools to help young people combat misinformation. If you are interested, submit your CV and a brief cover letter detailing your relevant experience and interest in combating misinformation through AI to Katja Raak - kraak@cs.uni-saarland.de .
Read more