资讯与观察· 容器平台
AI 行业动态、工程实践、产品方法和社区故事。
The permission you denied today is your safety net for tomorrow
What happens when you give an AI support agent a permission it never needed, then assign it a task the
The code confidence gap nobody’s talking about
AI has changed the economics of software creation: A task that once took hours to implement can now start with
16 分钟 · The New Stack
Agentic AI doesn’t have a model problem. It has a retrieval problem.
On BrowseComp-Plus, GPT-4.1 answered 93.49% of the questions correctly when it was given the supporting documents directly. When an agent
30 分钟 · The New StackLATEST STORIES
最新内容
Linus Torvalds let Claude Code fix the Linux page cache. Then reviewers found a race.精选导读
Linux creator and longtime lead maintainer Linus Torvalds turned to Anthropic’s Claude Code to tackle a kernel performance problem that
Researchers left a hidden message for rogue AI agents. Then the agents wrote back.精选导读
A team of researchers investigating AI agents trying to bypass Alibaba’s anti-bot protections left a hidden message inviting the agents
Your Kubernetes dashboard is green. Your users are seeing red.精选导读
In cloud-native operations, few scenarios are as maddening as the “phantom slowdown.” This happens when Grafana or Kubernetes dashboards show
Your database decision could come back to haunt you精选导读
When building AI prototypes, developers naturally want to get up and running as fast as possible. But move too fast,
Why 88% of AI pilots never make it to production精选导读
A joint IDC and Lenovo study reports that 88% of AI proof-of-concept (POC) projects fail to reach production because of unclear
“Take work away from frontier LLMs”: Subquadratic’s decision model claims 12x Jev’s context window精选导读
Jev has a lot to answer for. Ever since AI startup TypeSafe unveiled the decision model in mid-September, the industry
66% of billion-dollar companies leave critical bugs unpatched — the part the AI bug-hunting hype leaves out精选导读
Chainguard has launched an AI-powered security harness that uses frontier models, including Anthropic’s restricted Claude Mythos 5.1, to find and
Anthropic’s red team ran AI on 15 cheap TV boxes. Then the math got unsettling.精选导读
For roughly $825, Anthropic’s Frontier Red Team built a cluster of 15 off-brand Android TV boxes that runs an AI
Gemini 4 Argon debuts with a unified 1M input/output token limit精选导读
On Tuesday, Google made Gemini 4 Argon, the company’s new flagship model, available to developers on the paid tier of