A six-hour prompt asked Claude Opus 5.5 to build a Three.js visualization of the 55 imaginary cities in Italo Calvino’s Invisible Cities, without asking follow-up questions. Repeating the experiment in two configurations produced broadly similar results to data-visualization specialist Piotr Migdał’s version, which the author judges slightly better visually. The higher-effort run, using an additional coding tool, yielded a more impressive visualization but failed to support mouse input reliably. It cost about $265, versus $15 for the medium-effort run, and used roughly 17 times as many output tokens; summed API time across parallel agents was about 16.5 hours, though active elapsed time was under two hours. The author shares the interactive projects, code, and agent transcripts, and invites others to try the prompt.
The experiment also prompts a wider reflection on AI and professional identity. The author argues that programmers’ anger, alienation, and sense of lost independence resemble the distress experienced by skilled workers during the Industrial Revolution, whose accounts and petitions described machines undermining their craft. This makes today’s anxiety neither unique nor limited to programmers: scientists and other white-collar workers may face similar disruption as AI agents take on more work. The author expects occupations to change rather than simply disappear, and draws encouragement from Go, where human play improved after AlphaGo’s arrival. AI may unsettle people’s sense of purpose, but its influence can also push human skill and performance in new directions.
Summary generated by AI from the linked article. hn.today is not affiliated with Hacker News or Y Combinator.
Google AI Mode sometimes avoids directly saying Joe Biden won the 2020 US presidential election, instead directing users to official sources. Its responses vary across users and election years, while answers become more direct when asked outside the US. (arstechnica.com)
AI data centers can consume millions of gallons of water daily, competing with local communities for drinking water as their numbers grow. Residents around the world are organizing to oppose projects that threaten local water supplies. (restofworld.org)
Cartesia argues that tokenizers limit end-to-end learning because they impose hand-crafted text boundaries. Its hierarchical networks learn to group raw bytes into useful units, offering a scalable path toward byte-level language models. (cartesia.ai)
Particle-1 is a software-engineering model post-trained on DeepSeek V4.1 Flash that uses about 45% fewer tokens while maintaining comparable accuracy. Across four coding and data-engineering benchmarks, it cuts average task costs by 34.4%-51.6%, with plans to expand into other domains. (particle.ai)
Google’s Gemini gave different results for two election-related queries that differed by one digit, according to an X post. The post claims one result censored Joe Biden but does not show the queries or responses. (twitter.com)
Google introduced Gemini 4 Carbon, a new model in its Gemini lineup. The announcement describes the model and its capabilities. (blog.google)
Today's best Hacker News stories, summarized and screenshotted, one email a day.