Browsing Tag
LLM
105 posts
AI Hallucination Squatting: The New Agentic Attack Vector
IT InstaTunnel Team Published by our engineering team AI Hallucination Squatting: The New Agentic Attack Vector AI Hallucination…
[Tutorial] From Agents to APIs: Building Production-Ready AI Systems with Google ADK & FastAPI
Building production-ready AI systems requires a shift from simple prompting to structured orchestration. Using the Google Agent Development…
Reducing LLM Cost and Latency Using Semantic Caching
Running large language models in production quickly exposes two operational realities: every request costs money, and every request…
Fast Searching 4 Million Patent Records with FTS5
Introduction: The Limitations of LIKE Search When searching for “battery” in PatentLLM’s patent database (4 million records), results…
GPT-5.4 Is Here? No. But Here’s What Developers Actually Need to Know About GPT-5
GPT-5.4 Is Here? No. But Here’s What Developers Actually Need to Know About GPT-5 I got three Slack…
Monitor LLM Inference in Production (2026): Prometheus & Grafana for vLLM, TGI, llama.cpp
LLM inference looks like “just another API” — until latency spikes, queues back up, and your GPUs sit…
Coding Agent Teams Outperform Solo Agents: 72.2% on SWE-bench Verified
Most AI coding agents work alone. You give them an issue, they figure it out, they hand you…
Best AI Models for Coding in 2026: Claude, GPT-5, Gemini, and DeepSeek Compared
Best AI Models for Coding in 2026: Claude, GPT-5, Gemini, and DeepSeek Compared Picking the right coding model…
Serving LLMs on IaaS: throughput vs latency tuning with practical guardrails
Serving LLMs on IaaS is queueing plus memory pressure dressed up as ML. Every request has a prefill phase (prompt → KV…
