METR 警告称,人工智能的进步速度快于专家能够可靠地测试新系统是否安全的速度
原文:AI is getting better faster than experts can reliably test whether new systems are safe, METR warns
英文正文:点「译成中文」可整篇机器翻译(免费通道,不花钱),翻好永久缓存、下次秒开。
METR reports that leading AI models like Opus 5.5 and GPT-6 Astra are improving rapidly at research tasks but getting harder to measure.该组织警告说,目前的数据不能排除人工智能发展出现危险加速的可能性,不过它也表示,常见的测试可能会高估模型的实际功能。 The article AI is getting better faster than experts can reliably test whether new s
AI models are rapidly improving at AI research tasks, and they're getting harder to measure. According to the AI research organization METR , current public data isn't enough to rule out a drastic acceleration in AI research over the next few years. That could leave humans unable "to meaningfully understand, assess, and react to catastrophic risks posed by new AI systems," the organization warns.
On clearly defined coding and computational tasks with direct feedback, the models already beat experienced human professionals most of the time, METR found, though they haven't yet outperformed large groups of top experts. For tasks that take humans longer, the task length the models can handle doubles every 3.6 months.
A naive extrapolation of METR's data puts them at a 50 percent success rate on the longest, 200-hour tasks by July 2027.
The systems still struggle with open-ended questions that lack immediate feedback and require real judgment, as well as with situations that are hard to recreate for training, according to METR. The organization also warns that common, easy-to-run tests may overestimate how well the models perform in real-world use, since developers train them in very similar test environments.
Source: METR
Earlier coverage Security researchers show how cheap AI inference providers steal keys and snoop on users OpenAI opens its AI systems to four independent on-site auditors for the first time
"Ask AI" with your Decoder subscription
- AI perspectives on the topic
- More context from the archive
- Get technical terms explained
- Ask your own questions
Ask AI Beta
Ask a question about the article or an AI topic. You can ask follow-up questions.
正文由本站服务器抓取保存(已自动过滤广告、推荐位与追踪图片),排版与原站可能不同;版权归原站所有。