Skip to content
PHP2Shell: The PHP Bug
Akshay Thakare

Generative AI

How LLM applications are built, evaluated and shipped.

4 notes · all topicsGenAI & LLMs

Start here · beginner3

  1. 1How LLMs Generate Text, One Token at a TimeTokens, probabilities, sampling and context windows — the mental model every GenAI engineer needs.
  2. 2Tokens, Context Windows and SamplingWhat a token is, why the context window limits everything an LLM sees, and how temperature and top-p change its answers.
  3. 3Prompting for Engineers: Structured Outputs Over Clever WordingTreat a prompt like an API contract: clear instructions, examples, a strict output schema and validation — so LLM output can safely feed a pipeline.

Next · intermediate1

  1. 4Hallucinations and How to Ground an LLMWhy LLMs state false things confidently, and the practical techniques that reduce it: grounding, citations, constrained outputs and checks.