LLM Archives - GITERROR

How to Actually Abuse LLMs

Understanding an LLM’s edges matters more than flattering it.
This post explores how deliberately pushing models into conflicting, noisy, or chained prompts reveals their failure modes — and why learning those edges is the core of real prompt engineering.

By michal, 3 weeksFebruary 14, 2026 ago

Why LLMs Hallucinate — Patterns, Pitfalls, and How to Guard Against It

Hallucination isn’t a mystery glitch — it’s a predictable consequence of how LLMs work. This Field Note breaks down why models fabricate information, the patterns behind it, and practical ways to reason about and mitigate hallucination in real systems.

By michal, 4 weeksFebruary 7, 2026 ago

Artificial intelligence (AI) LLM RAG

How to Build Reliable LLM Pipelines — Grounding, Verification, and Resilience

LLM pipelines aren’t just prompts and models — they’re grounded, verified, cached, and resilient systems. This Field Note breaks down pragmatic patterns like retrieval grounding, verification checks, caching strategies, and reliability practices that keep AI systems dependable beyond demos.

By michal, 1 monthFebruary 1, 2026 ago

Artificial intelligence (AI) AWS GenAI LLM

Getting Started with Amazon Bedrock

Amazon Bedrock lowers the barrier to building generative AI applications by providing unified, serverless access to leading foundation models without managing infrastructure. This guide walks through the fundamentals of getting started with Bedrock — from enabling model access and running first prompts to understanding how Bedrock fits into modern AWS architectures and real-world AI development workflows.

By michal, 1 yearDecember 30, 2024 ago

Artificial intelligence (AI) LLM

Foundation Models (FMs) in 2024: A Practical Guide to Choosing the Right Model

Foundation models are evolving faster than most teams can evaluate them. This practical guide cuts through benchmark hype to explain how to actually choose the right model for real-world workloads — balancing capability, cost, latency, reasoning quality, and operational constraints. Instead of chasing the “best” model, the post focuses on matching models to use cases and building a repeatable decision framework for production AI systems.

By michal, 1 yearDecember 29, 2024 ago