AI幻觉率仅0.2%，却让生产流程空转245次，一场关于AI可靠性的真实事故复盘。
We run ~100 LLM agents unattended on local models. Last week we found one document that had been rewritten 245 times in 5 days — every attempt rejecte…
从真实翻车中提炼的20条Claude Code技能，专治“看起来会了”的AI编程幻觉。
Article URL: https://whetstone.akbarsha.dev/ Comments URL: https://news.ycombinator.com/item?id=49235255 Points: 3 # Comments: 0
Meta AI团队重组为何引发史上最严重混乱？揭秘巨头战略决策的深层教训
Article URL: https://www.inc.com/jessica-stillman/the-worst-its-ever-been-why-metas-massive-ai-reorg-backfired-spectacularly/91363370 Comments URL: ht…
研究表明大模型在医疗场景中高度敏感于提示变化，可能从可靠变错误，警示临床部署风险
arXiv:2606.07237v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used in healthcare for tasks such as clinical question…
查询Google已关闭产品的数据库，帮助产品经理和开发者避免重蹈覆辙，是复盘失败案例的利器。
A Swiss Army knife is a terrible knife. It's a terrible screwdriver, a terrible bottle opener, and a terrible saw. The only thing a Swiss Army knife i…
加盟商怒告必胜客，揭露厨房AI部署失败的代价与行业警示。
Article URL: https://www.theregister.com/ai-ml/2026/05/19/frustrated-franchisee-sues-pizza-hut-over-crappy-kitchen-ai/5242899 Comments URL: https://ne…