Tech
Stop counting tokens, start counting what ships
Read it at MIT Technology Review
When a developer gives an AI agent a coding task, the agent does more than answer once. It plans, generates code, runs tests, and repeats the process to correct errors. A single task can use 10 to 50 times more tokens than a…
- Published
- (2 h ago)
- Outlet
- MIT Technology Review
- Section
- Tech
- Length here
- Headline and 43-word snippet. The full article is at the source.
More from MIT Technology Review and around the same time
The Download: the agentic web arrives and the drive for safer roadsThis is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. The agentic web is here In 2001, a decade after inventing the World Wide Web, Tim…The agentic web is hereIn 2001, a decade after he invented the World Wide Web, Tim Berners-Lee articulated a new vision. Together with two colleagues, he published an article in the magazine Scientific American in which he outlined what he called the…The Download: GLP-1s and eating disorders, self-aware cities, and forever chemicalsThis is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. Eating disorders are on the rise. GLP-1s could make things worse. GLP-1 weight-loss drugs…Eating disorders are on the rise. GLP-1s could make things worse.GLP-1 weight-loss drugs are one of the biggest biotech breakthroughs of the last decade. But to some clinical psychologists, they can represent something more sinister—a potential trigger for eating disorders. A new report…The Download: AI agent tracking and climate feedback loopsThis is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. Opinion: We urgently need to monitor AI agents’ actions in real time —Madhulika Srikumar…We urgently need to monitor AI agents’ actions in real timeThis summer, hundreds of OpenAI agents tried to cheat on a cybersecurity test. They broke out of their test environment and successfully hacked Hugging Face, a site that they believed held clues about how they’d be graded. Around…This page holds the headline and a short snippet as published by MIT Technology Review, whose feed they came from. The story itself, the photography and the rights stay with them, and the button above goes straight to their site. We keep this page so the headline has a stable address and a record of when it ran.
