corpus.blog
41554 blogs · [ { "id": "01a087e7-963f-7189-95ea-4963d4cd24fe", "title": "One Cable, 200 Gbit/s: Connecting Two GB10 Systems with ConnectX-7", "url": "https://www.subhashdasyam.com/2026/07/one-cable-200-gbits-connecting-two-gb10.html", "published_at": "2026-07-18T15:56:44+00:00" }, { "id": "01a087e7-963f-7189-95ea-4963d58fb9f1", "title": "Introducing DVAIB - Damn Vulnerable AI Bank", "url": "https://www.subhashdasyam.com/2025/12/damn-vulnerable-ai-bank.html", "published_at": "2025-12-27T16:44:00+00:00" }, { "id": "01a087e7-963f-7189-95ea-4963d6597610", "title": "Multi-Turn Jailbreaks and “Psychological Manipulation” Attacks: Why Single-Turn Defenses Fail", "url": "https://www.subhashdasyam.com/2025/12/multi-turn-ai-jailbreaks-and-psychological-manipulation-attacks.html", "published_at": "2025-12-23T19:47:00+00:00" }, { "id": "01a087e7-963f-7189-95ea-4963d7539bc1", "title": "KV Cache Security for Long-Context LLM Inference", "url": "https://www.subhashdasyam.com/2025/12/long-context-inference-security-kv.html", "published_at": "2025-12-23T18:01:57+00:00" }, { "id": "01a087e7-963f-7189-95ea-4963d78b0cc0", "title": "Policy-as-Code for AI Workloads in Kubernetes: Kyverno/OPA Patterns for Model and Data Safety", "url": "https://www.subhashdasyam.com/2025/12/policy-as-code-for-ai-workloads-in-kubernetes.html.html", "published_at": "2025-12-23T17:26:17+00:00" }, { "id": "01a087e7-963f-7189-95ea-4963d86b2e05", "title": "Securing Agentic AI: Roadmap Part-10", "url": "https://www.subhashdasyam.com/2025/12/securing-agentic-ai-roadmap-part-10.html", "published_at": "2025-12-07T16:48:00+00:00" }, { "id": "01a087e7-963f-7189-95ea-4963d92bf21a", "title": "Securing Agentic AI: Governance Framework Part-9", "url": "https://www.subhashdasyam.com/2025/12/securing-agentic-ai-governance.html", "published_at": "2025-12-07T10:59:00+00:00" }, { "id": "01a087e7-963f-7189-95ea-4963d9a003bf", "title": "Securing Agentic AI: Enterprise Integration Part-8", "url": "https://www.subhashdasyam.com/2025/12/securing-agentic-ai-enterprise.html", "published_at": "2025-12-07T10:51:01+00:00" }, { "id": "01a087e7-963f-7189-95ea-4963da740f93", "title": "Securing Agentic AI: Secure Architecture Patterns Part-7", "url": "https://www.subhashdasyam.com/2025/12/securing-agentic-ai-secure-architecture.html", "published_at": "2025-12-07T10:45:05+00:00" }, { "id": "01a087e7-963f-7189-95ea-4963db048ae8", "title": "Securing Agentic AI: Identity and Access Control for Agents Part-6", "url": "https://www.subhashdasyam.com/2025/12/securing-agentic-ai-identity-and-access.html", "published_at": "2025-12-07T10:40:00+00:00" }, { "id": "01a087e7-963f-7189-95ea-4963db0cf9ae", "title": "Securing Agentic AI: Threat Landscape for Agentic Systems Part-5", "url": "https://www.subhashdasyam.com/2025/12/securing-agentic-ai-threat-landscape.html", "published_at": "2025-12-07T10:35:00+00:00" }, { "id": "01a087e7-963f-7189-95ea-4963db5f4d93", "title": "Securing Agentic AI: Human in the Loop (HITL) Design Patterns Part-4", "url": "https://www.subhashdasyam.com/2025/12/securing-agentic-ai-architecture_7.html", "published_at": "2025-12-07T10:28:00+00:00" }, { "id": "01a087e7-963f-7189-95ea-4963dbfe0bcf", "title": "Multi-Agent AI Security: Trust Boundaries and Handoffs (Part 3)", "url": "https://www.subhashdasyam.com/2025/12/securing-agentic-ai-architecture_64.html", "published_at": "2025-12-06T16:00:00+00:00" }, { "id": "01a087e7-963f-7189-95ea-4963dccd809d", "title": "Securing Agentic AI: Agent Architecture Patterns - Security Analysis Part-2", "url": "https://www.subhashdasyam.com/2025/12/securing-agentic-ai-architecture_6.html", "published_at": "2025-12-06T15:53:00+00:00" }, { "id": "01a087e7-963f-7189-95ea-4963dcf5364e", "title": "Securing Agentic AI: Architecture, Patterns, and Governance for Enterprise Adoption Part-1", "url": "https://www.subhashdasyam.com/2025/12/securing-agentic-ai-architecture.html", "published_at": "2025-12-06T15:06:00+00:00" }, { "id": "01a087e7-963f-7189-95ea-4963dd7c0096", "title": "Building Privacy-Preserving RAG with Homomorphic Encryption", "url": "https://www.subhashdasyam.com/2025/11/building-privacy-preserving-rag-with.html", "published_at": "2025-11-05T18:13:00+00:00" }, { "id": "01a087e7-963f-7189-95ea-4963ddb4cf02", "title": "AI's Dirty Secret: Embedding Inversion and Privacy Risks Explained", "url": "https://www.subhashdasyam.com/2025/10/ais-dirty-secret-embeddings-are-just.html", "published_at": "2025-10-27T18:27:00+00:00" }, { "id": "01a087e7-963f-7189-95ea-4963ddfbf339", "title": "Securing Claude Code for macOS on Enterprise Environments", "url": "https://www.subhashdasyam.com/2025/10/securing-claude-code-for-macos-on.html", "published_at": "2025-10-07T11:13:00+00:00" }, { "id": "01a087e7-963f-7189-95ea-4963de29ab9f", "title": "Securing Claude Code for Windows Enterprise Deployments: A Comprehensive Security Framework", "url": "https://www.subhashdasyam.com/2025/10/securing-claude-code-for-windows.html", "published_at": "2025-10-06T21:46:00+00:00" }, { "id": "01a087e7-963f-7189-95ea-4963de4483e0", "title": "Enterprise MCP Security Architecture: A Production Guide", "url": "https://www.subhashdasyam.com/2025/09/building-enterprise-mcp-architecture.html", "published_at": "2025-09-27T12:58:00+00:00" }, { "id": "01a087e7-963f-7189-95ea-4963de453c7f", "title": "FP32 vs FP16 vs BF16 vs FP8 vs INT8 vs INT4: AI Precision Guide", "url": "https://www.subhashdasyam.com/2025/08/decoding-fp32-fp16-fp8-int8-int4-master.html", "published_at": "2025-08-13T20:41:00+00:00" }, { "id": "01a087e7-963f-7189-95ea-4963de4f2191", "title": "Mixture of Experts (MoE): The Specialist Consultant Revolution 🏢", "url": "https://www.subhashdasyam.com/2025/07/mixture-of-experts-moe-specialist.html", "published_at": "2025-07-13T19:00:00+00:00" }, { "id": "01a087e7-963f-7189-95ea-4963df433096", "title": "How Transformers Actually Work: The Complete Simple Guide 🤖", "url": "https://www.subhashdasyam.com/2025/07/how-transformers-actually-work-complete.html", "published_at": "2025-07-07T20:45:00+00:00" }, { "id": "01a087e7-963f-7189-95ea-4963dfe5e324", "title": "A Few of the Crazy Ways to Secure Secrets on Kubernetes / OpenShift", "url": "https://www.subhashdasyam.com/2025/06/a-few-of-crazy-ways-to-secure-secrets.html", "published_at": "2025-06-18T16:36:00+00:00" }, { "id": "01a087e7-963f-7189-95ea-4963dff06eff", "title": "RAG+ Revolution: How Application-Aware Reasoning Transforms AI Knowledge Systems", "url": "https://www.subhashdasyam.com/2025/06/rag-revolution-how-application-aware.html", "published_at": "2025-06-17T10:48:00+00:00" } ] posts Claim your blog
Back to subhashdasyam.com
Blog · corpus.blog/blogs/subhashdasyam.com/posts

subhashdasyam.com

subhashdasyam.com

2026

One Cable, 200 Gbit/s: Connecting Two GB10 Systems with ConnectX-7original ↗
18 Jul 2026

2025

Introducing DVAIB - Damn Vulnerable AI Bankoriginal ↗
27 Dec 2025
Multi-Turn Jailbreaks and “Psychological Manipulation” Attacks: Why Single-Turn Defenses Failoriginal ↗
23 Dec 2025
KV Cache Security for Long-Context LLM Inferenceoriginal ↗
23 Dec 2025
Policy-as-Code for AI Workloads in Kubernetes: Kyverno/OPA Patterns for Model and Data Safetyoriginal ↗
23 Dec 2025
Securing Agentic AI: Roadmap Part-10original ↗
7 Dec 2025
Securing Agentic AI: Governance Framework Part-9original ↗
7 Dec 2025
Securing Agentic AI: Enterprise Integration Part-8original ↗
7 Dec 2025
Securing Agentic AI: Secure Architecture Patterns Part-7original ↗
7 Dec 2025
Securing Agentic AI: Identity and Access Control for Agents Part-6original ↗
7 Dec 2025
Securing Agentic AI: Threat Landscape for Agentic Systems Part-5original ↗
7 Dec 2025
Securing Agentic AI: Human in the Loop (HITL) Design Patterns Part-4original ↗
7 Dec 2025
Multi-Agent AI Security: Trust Boundaries and Handoffs (Part 3)original ↗
6 Dec 2025
Securing Agentic AI: Agent Architecture Patterns - Security Analysis Part-2original ↗
6 Dec 2025
Securing Agentic AI: Architecture, Patterns, and Governance for Enterprise Adoption Part-1original ↗
6 Dec 2025
Building Privacy-Preserving RAG with Homomorphic Encryptionoriginal ↗
5 Nov 2025
AI's Dirty Secret: Embedding Inversion and Privacy Risks Explainedoriginal ↗
27 Oct 2025
Securing Claude Code for macOS on Enterprise Environmentsoriginal ↗
7 Oct 2025
Securing Claude Code for Windows Enterprise Deployments: A Comprehensive Security Frameworkoriginal ↗
6 Oct 2025
Enterprise MCP Security Architecture: A Production Guideoriginal ↗
27 Sept 2025
FP32 vs FP16 vs BF16 vs FP8 vs INT8 vs INT4: AI Precision Guideoriginal ↗
13 Aug 2025
Mixture of Experts (MoE): The Specialist Consultant Revolution 🏢original ↗
13 Jul 2025
How Transformers Actually Work: The Complete Simple Guide 🤖original ↗
7 Jul 2025
A Few of the Crazy Ways to Secure Secrets on Kubernetes / OpenShiftoriginal ↗
18 Jun 2025
RAG+ Revolution: How Application-Aware Reasoning Transforms AI Knowledge Systemsoriginal ↗
17 Jun 2025