Amazon finds cases of AI causing runaway spending on tech projects - FT中文网
登录×
电子邮件/用户名
密码
记住我
请输入邮箱和密码进行绑定操作:
请输入手机号码,通过短信验证(目前仅支持中国大陆地区的手机号):
请您阅读我们的用户注册协议隐私权保护政策,点击下方按钮即视为您接受。
商业快报

Amazon finds cases of AI causing runaway spending on tech projects

E-commerce giant’s staff said the new technology had caused budget overruns that sometimes took months to detect
00:00

{"text":[[{"start":8.72,"text":"Amazon staff have identified cases of what they called “catastrophically expensive” cost overruns caused by mistakes in how the company has deployed AI and a lack of spending controls."}],[{"start":20.38,"text":"Senior engineers told colleagues in a staff meeting on Tuesday that attempts to switch tasks from conventional programming to using AI models had led to “unplanned” spending, said multiple people familiar with the matter."}],[{"start":32.88,"text":"Engineers were working to create “automated” guardrails for future projects, among other measures to keep a lid on costs, the people said."}],[{"start":39.72,"text":"The episode highlights the difficulty that even the biggest tech companies are having integrating AI into their daily operations without overspending."}],[{"start":47.6,"text":"“It’s difficult to figure out how much anything [AI related] costs,” one senior Amazon employee told the FT."}],[{"start":54.52,"text":"During a presentation this week, employees were told about one instance in which the company spent $1.8mn on matching author details with listings on the group’s ecommerce website using Anthropic’s Claude Sonnet AI model despite the deployment failing, the people said."}],[{"start":70.72,"text":"The spending represented an 860 per cent cost overrun compared to the project’s budget and took five months to detect, they added."}],[{"start":78.84,"text":"Amazon said: “As with any new technology, we’re experimenting, learning and improving how we use it, including how we drive cost efficiencies.”"}],[{"start":87.68,"text":"Staff were told coding mistakes that were “trivially cheap” in traditional systems were proving “catastrophically expensive” as teams started to deploy AI models to complete tasks."}],[{"start":97.86,"text":"Senior engineers told staff that the overspending was not an “isolated” incident. In a separate episode, the company incurred roughly $541,000 in unexpected costs related to building financial auditing tools."}],[{"start":110.56,"text":"A third incident, in which AI was being used to improve delivery speeds across its logistics network, incurred $134,000 in accidental spending and took more than a fortnight to detect."}],[{"start":122.72,"text":"The company added: “Cherry-picking small, isolated examples where teams are learning from one another and portraying them as business as usual doesn’t reflect how teams across Amazon are using AI.”"}],[{"start":132.96,"text":"The presentation noted these examples spanned only a handful of teams at Amazon, which employs roughly 300,000 corporate staff and makes about $180bn in revenue each quarter."}],[{"start":144.32,"text":"The $2.5tn group is undertaking sweeping lay-offs in an attempt to reduce its costs and help finance its vast AI investment. Amazon this year is expected to spend $200bn in capital expenditure, the vast majority of which will go towards AI and data centre infrastructure."}],[{"start":163.12,"text":"Companies have been grappling with an increase in the cost of deploying AI tools as providers shift their pricing models. AI labs including Anthropic and OpenAI have transitioned some services from flat subscriptions to token-based billing, which tracks the units of data processed by models."}],[{"start":180.76,"text":"Changes in AI pricing models have led companies to shift their AI usage away from the most advanced models to cheaper mid-tier versions and alternatives, including open-weight models that only require users to pay for the computing power needed to run them."}],[{"start":195.32,"text":"Amazon earlier this year shuttered an internal leaderboard that ranked employees’ use of its Kiro developer platform after it led to so-called “tokenmaxxing”, with employees inflating their consumption of AI tokens."}],[{"start":207.64,"text":"Executives at the group told employees the service had been created with “good intentions” but ultimately ran up costs, the FT previously reported."}],[{"start":220.64,"text":""}]],"url":"https://audio.ftcn.net.cn/album/a_1785413726_9510.mp3"}

版权声明:本文版权归FT中文网所有,未经允许任何单位或个人不得转载,复制或以任何其他方式使用本文全部或部分,侵权必究。

谷歌为Anthropic打造的2000亿美元华尔街融资机器

私募信贷、芯片租赁和数据中心担保,支撑起AI支出的全新庞大模式。

“日元干预”等于“美国自保”

美国联手日本支撑日元,不只是出于盟友情谊,更是为了避免日本加息或美国国债遭抛售、导致美债收益率进一步走高。

“诅咒之岛”:科技游民与诈骗犯藏身的千亿美元奢华开发项目

警方的突击搜查再次打击了马来西亚陷入困境的中资“森林城市”项目的声誉。

问题不在因凡蒂诺

马杜罗:应该将国际足联的监管职能与商业活动分开,其治理应真正做到包容并具有代表性,监督必须真正独立。

俄罗斯扩大“影子”液化天然气船队,应对欧盟禁令

随着明年制裁进一步收紧,越来越多的“影子”船舶将帮助俄罗斯继续出口液化天然气。

阿斯利康与百时美施贵宝:大药企有时也不够大

当资产负债表规模扩大、能够押注潜在重磅药物时,规模才会带来优势。
设置字号×
最小
较小
默认
较大
最大
分享×