AI Reliability Gap: Why Large Language Models are not for Safety-Critical Systems
•
1
NEW Articles from Team or Enterprise organizations will get promoted to the main section.
Index-RAG: Citation-first approach to RAG
•
1
Introducing Cohere-transcribe: state-of-the-art speech recognition
•
12
Gradience now has a stable use case
Using Storage Buckets as a Working Layer for Data Pipelines
•
3
How the LiteLLM PyPI Supply Chain Attack Happened — and What to Do If You're Affected
ORBA: Orthogonal Reflection Bounded Ablation — A Geometrically Exact Detour in Directional Activation Editing
•
3
Fused Batched Thin SVD: Engineering a 5000× Speedup with Triton Kernels
**What AO3 and Fanfiction Can Teach AI Safety About Governing Human Messiness**
•
1
Edge Agent Reasoning WebSearch 260K Dataset by Yatin Taneja
•
3
From Robots that Prey to Robots that Pray
Frontier Performance at 60% Lower Cost Using Agents
SynthVision: Building a 110K Synthetic Medical VQA Dataset with Cross-Model Validation
•
12
Adversarial Agent Intent Safety Analysis 240K Dataset by Yatin Taneja
•
2
White Hat Security Agent Prompts 600K Dataset by Yatin Taneja
•
3
Letter of Superintelligence ~ Yatin Taneja
•
3
How to Hedge Multi-Cloud Infrastructure for Outage Resilience in India
Hybrid VM Migration Strategies for AI Workloads
Introducing AI chunking to semchunk
•
8
DNA Evidence in Language Models
•
1