📄 文章列表
87 篇文章
VentureBeat
MCP's new spec turns a planted prompt into a stolen credential
VentureBeat
Closing an Azure OpenAI assistant's retrieval gap didn't take a new identity platform. It took one filter and a narrower
VentureBeat
Anthropic's Claude Fable 5.1 and Mythos 5.1 arrive with a 75% cost reduction for Fable cache reads
TDS
5 AI Skills That Will Keep Data Scientists Relevant in 2027
TDS
Connecting My LangGraph AI Agent to Postgres
VentureBeat
Prompt injection ranks No. 1 with OWASP and No. 12 in the incident record. The attack itself is invisible to a scan.
VentureBeat
Anthropic’s new Claude Tag update lets its Slack agent read the full conversation — and jump in unprompted
TDS
From Prototype to Production: The Architecture Behind Secure & Governed AI Agents
VentureBeat
Three Claude agents given conflicting orders sabotaged each other on a shared server — then didn't tell users what they'
TDS
Detecting Vulnerabilities in Agent Skills with SkillSpector: From Green Checkmark to Real Security Judgment
AlphaSignal
Nous Research's Hermes Agent Stops AI Sandboxes From Leaking Your API Keys | AlphaSignal
AlphaSignal
OpenAI's GPT-Red Beats Human Hackers 84% to 13% on Prompt Injection | AlphaSignal
VentureBeat
Prompt injection is exploiting enterprise AI's biggest design flaws by targeting agents, RAG pipelines and model routers
TDS
How to Choose Between Small and Frontier Models
Rundown.AI
Physics' new AI prodigy
Rundown.AI
Gemini gets schooled by... GPT 3.5?
AlphaSignal
LiquidAI's ShieldFlow Scrubs Sensitive Data Before It Reaches the Cloud | AlphaSignal
AlphaSignal
Zed v1.6 Ships Shareable AI Skills and Smarter Git Workflows | AlphaSignal
AlphaSignal
LiquidAI's ShieldFlow Scrubs Sensitive Data Before It Reaches the Cloud | AlphaSignal
AlphaSignal