@can: isn’t computer use like an insane waste of tokens? I don’t think anyone really cares and neither should they maybe but …
Summary
A practitioner questions whether computer-use AI agents are an inefficient waste of tokens, asking about the underlying economics of agentic browser/desktop automation.
Similar Articles
Asking for real perspectives: has your workplace gone all in on AI agents?
A community discussion asking whether companies are going all-in on AI agents, prompted by an anecdote about an energy company replacing programmers with Claude-based agents and spending heavily on tokens. The post questions long-term savings once token costs and lost system knowledge are factored in.
@kentcdodds: I know we're all really excited about computer use and how powerful that is, but there's a reason that @OpenAI and othe…
Computer use with LLMs is about 45 times more expensive than using structured APIs due to high token costs from screenshots. A hybrid approach is recommended, using structured APIs for most tasks and computer use only when necessary.
Is AI automation actually helping you at work, or are we just burning insane token budgets to justify layoffs?
Reflects on the mixed impact of AI automation in enterprises, noting that efficiency gains are often used to justify layoffs while token budgets may be wasteful. Raises data privacy concerns about AI agents accessing work communication platforms.
Am I antiquated, or do a lot of the ways people use AI agents make no sense?
A critical opinion piece questioning the practical utility of many current AI agent use cases, arguing that deterministic or manual solutions are often more reliable and simpler.
You can't solve computer use by ignoring the interface
This article argues that current AI computer-use agents often bypass the actual user interface by directly accessing APIs or scripting, leading to inflated benchmark results and unreliable real-world performance. It suggests that ignoring the interface is a flawed approach that does not generalize to messy GUI environments.