Skip to content

Category

Engineering

Page 2 of 2

Engineering

A practical checklist for picking an LLM for your feature

How LLM inference actually works: prefill vs decode

When no single model is enough: the primary and verifier pattern

Common failure modes in LLM systems — and how to catch them

Stop ranking LLMs, start profiling them

Defending against prompt injection and jailbreaks — and reducing hallucination

Fine-tune your first model on free Colab: QLoRA in about 40 lines

A 70B model on one GPU: a practical guide to quantization

Save first, then publish: a simple rule for not losing work

The rule layer: deterministic guardrails around a probabilistic model

Tracing a request through a multi-agent system

What quantization actually does: precision loss and vector-space collapse

Where LLM serving costs actually go

Why LoRA works: the intrinsic-dimensionality story

From worker to specialist: an agent that owns a domain

Working with LLM APIs: first calls, tokens, and structured output

Zero-shot, few-shot, or chain-of-thought: picking the right technique