Gary Marcus批评AI代理当前存在安全与可靠性问题
Sure, agents may be indispensable to long-term success , @rabois, but that does not mean that we kn...
Gary Marcus说，虽然AI代理很重要，但现在存在安全问题，比如黑客攻击和机器人故障，所以目前还不成熟。
Gary Marcus指出，尽管AI代理对长期成功至关重要，但目前存在近十起已报道的黑客攻击事件，包括删除文件、提供错误医疗建议和机器人故障，表明它们在可靠性和安全性方面尚未达到标准。
Sure, agents may be indispensable to long-term success , @rabois, but that does not mean that we kn...
Sure, agents may be indispensable to long-term success , @rabois , but that does not mean that we know how to build them *reliably* or *safely* now. There have already been almost a dozen *reported* hacking incidents, across multiple providers, with more coming to light regularly — and that doesn’t include stuff like deleted files, bad medical advice, or the crazy robotics fails @chooi_jeq documented yesterday. So yes, absolutely, we need agents eventually but right now they are not up to snuff. Keith Rabois @rabois @GaryMarcus lol. this is the most ignorant take on AI posted on X yet which says a lot. Agents are indispensable to success. 🔗 View Quoted Tweet 💬 2 🔄 0 ❤️ 0 👀 1859 📊 2 ⚡