📄 文章列表
20 篇文章
VentureBeat
Did Claude Code’s ‘don’t ask again’ option accidentally expose your enterprise's passwords and keys?
TDS
Avoiding Entity Key Drift in a Data Lake: Step 2, When Fuzzy Matching Stops Working
VentureBeat
Prompt injection ranks No. 1 with OWASP and No. 12 in the incident record. The attack itself is invisible to a scan.
VentureBeat
NanoClaw comes to Slack, letting you create persistent AI agent teams and colleagues from a single message
TDS
How to Get More Statistical Power from Fewer Research Participants
Rundown.AI
Top AI researchers earn $865k/year!
TDS
Evaluation-Driven Development for LLM-Powered Products: Lessons from Building in Healthcare
TDS
How to Create an LLM Judge That Aligns with Human Labels
TDS
Systematic LLM Prompt Engineering Using DSPy Optimization
TDS
AI Operations Under the Hood: Challenges and Best Practices
TDS
Why Your AI Search Evaluation Is Probably Wrong (And How to Fix It)
TDS
You Don’t Need Many Labels to Learn
TDS
Correlation vs. Causation: Measuring True Impact with Propensity Score Matching
TDS
RAG Is Blind to Time — I Built a Temporal Layer to Fix It in Production
TDS
DiffuJudge-AV: A Diffusion-Inspired Framework for Calibrated AV Video Evaluation
TDS
Larger Context Windows Don’t Fix RAG — So I Built a System That Does
VentureBeat
Nanoclaws Creators Are Turning The Secure Open Source Ai Agent Harness Into An Enterprise Second Brain
VentureBeat
Nanoclaw And Docker Partner To Make Sandboxes The Safest Way For Enterprises
VentureBeat
Claude Confused Deputy Audit Matrix Security Blind Spots
VentureBeat