MrComputerScience.com
Blog For Marketing And Tech Nerds
LLM APIs fail. Grok goes down, Claude starts rate limiting, Gemini returns 503s for twenty minutes. A naive retry loop hammers the failing endpoint until your budget is gone or your users give up. A …
Continue Reading about Implementing a Circuit Breaker for LLM API Calls in Rust →
Every tool you give an AI agent is a function an attacker can potentially call with arguments the attacker controls. Most agent security discussions focus on prompt injection in the user input. The …
Continue Reading about Why Your AI Agent’s Tool Calls Are an Attack Surface →
"Local" LLM does not always mean no network traffic. Ollama, LM Studio, and similar tools have telemetry, update checkers, and license verification that phone home by default. If you are running a …
Continue Reading about How to Audit What Your Local LLM Is Actually Sending to the Network →
Gemini 2.5 Pro advertises a 1 million token context window. I tested it against a real 100k token Python codebase to find out where the comprehension holds and where it fails. The answer is more …
Python agents get tool schema bugs at runtime. A Rust agent gets them at compile time, which is when you want them. This post builds a type-safe tool registry that serializes tool definitions to the …
Continue Reading about Building a Type-Safe Tool Registry for Multi-Model Agents in Rust →
Most developers skip evaluation entirely. They vibe-check their LLM app during development, ship it, and find out what is broken from user complaints. This is how you ship an agent that works great on …
Continue Reading about How to Run Evals on Your LLM App for Free in 2026 →
