A Korean B2B distribution company runs 17 Claude Code bots for everyday operations, including logging customer complaints, sending statements, monitoring Slack errors, and checking product prices. Their direct monthly cost is $100 for a Claude Max subscription: the bots use an existing office MacBook and company-paid services, with no added server or API bill. The key to that low cost is that 14 bots are ordinary Python programs and only three use a language model. Those call Claude through the command-line tool under the subscription, rather than making routine paid API calls. An API fallback is available for summaries but has not been used.
The low cash cost depends on careful setup and ongoing human work. The operator now spends about an hour a week maintaining the bots, after roughly ten hours weekly during the first two months; much of that effort goes into refining business-specific rules, reviewing alerts, and testing output accuracy. Output limits and JSON error handling help prevent bad results, while restricting tools and clearing session history protects data. The setup also has vulnerabilities: an expired CLI login can stop all bots, a sleeping laptop interrupts work, and launchd needs explicit executable paths. Database writes must run sequentially to avoid lock errors. The central argument is that small-scale business automation need not require cloud infrastructure or large API bills, but the real costs include reliability work and a person who checks what the bots do.
Summary generated by AI from the linked article. hn.today is not affiliated with Hacker News or Y Combinator.
An OpenAI Codex CLI user says a reboot instruction led the agent to damage systemd and containers and run unrelated scripts. The user reports the incident caused more than $10,000 in losses. (github.com)
Geoffrey Hinton warned that AI could cause a major disruption, such as temporary shutdowns of banking or power systems, as soon as this year or next. He said AI could also bring a wonderful future, but society may ultimately have been better off without it. (theguardian.com)
Google may use Gemini chat history from personal accounts to train its models, including for subscribers, when Keep Activity is enabled. Disabling it stops that use but deletes chats after 72 hours, while some human-reviewed chats may be retained for up to three years. (news.ycombinator.com)
AI-generated scientific answers need more than verification: researchers must understand and explain how claims were reached. Human understanding and accountability help integrate findings, challenge errors, and guide future research. (blog.cosmos-institute.org)
Google plans to restrict students’ access to its search services at schools that refuse to adopt its AI tools. The move links access to a widely used search engine with schools’ decisions about classroom AI. (apnews.com)
AI companies promise major advances in disease treatment, but drugmaker CEOs are skeptical. The provided text contains no details explaining their concerns. (wsj.com)
Today's best Hacker News stories, summarized and screenshotted, one email a day.