Ave Syah Shina

•Based in Semarang, Indonesia

Hmm... I'm just an average Information Engineering grad who loves digging in to build digital stuff that leaves a meaningful impression on people. I consider myself a full-stack software engineer, using AI, UI/UX design, and 3D Design to bring my ideas to the community. Check out my About page for the full story.

Download CV

// Blog

My latest writings.

01 — What Is AI Engineering? The Role, the Edge, and the Difference from ML

Is an AI Engineer just a rebranded ML Engineer? The boundary that cleared it for me: AI Engineers apply pre-trained models to real problems; training new ones from scratch is someone else's job.

Aug 13, 20267 min read

career
ai-engineering
ml
roadmap:ai-engineer
fundamentals

02 — How LLMs Work: Tokens, Training, Inference, and the Context Window

The next-token trick, unpacked. An LLM is a trained statistical engine: text becomes tokens, a transformer reads them, and the model samples the next token — again and again.

Aug 13, 20268 min read

llm
context
training
inference
tokens
roadmap:ai-engineer
embeddings
fundamentals

04 — Prompt vs Context Engineering: The System Prompt, the Role, the Constraints

'Writing good prompts' bundles two different skills. The split that mattered: prompt engineering crafts the instructions, context engineering builds the whole information environment around the model.

Aug 13, 20268 min read

prompt-engineering
llm
structured-output
system-prompt
roadmap:ai-engineer
context-engineering

03 — Sampling Knobs and Output Rails: Temperature, Top-K, Top-P, and the Rest

Temperature, top-p, max tokens: each knob looks like an isolated setting. The frame that collapsed them: every generation parameter reshapes the same next-token probability distribution before you sample.

Aug 13, 20268 min read

prompt-engineering
llm
temperature
top-p
top-k
roadmap:ai-engineer
sampling
fine-tuning

06 — Types of AI Models: Open, Closed, Pre-trained, and Self-hosted

'Open source good, closed source bad' breaks the moment you pick a real model. The three independent axes that actually decide: open/closed, pre-trained/from-scratch, self-hosted/cloud.

Aug 13, 20267 min read

closed-source
self-hosted
models
pre-trained
roadmap:ai-engineer
open-source
fundamentals

05 — Context Engineering in Practice: Few-Shot, ReAct, Compaction, and the Rest

Few-shot, ReAct, chain-of-thought, caching: unrelated tricks, or one pattern? Each one decides what goes in the context window, in what shape, and for how long.

Aug 13, 20268 min read

streaming
few-shot
react
prompt-caching
roadmap:ai-engineer
chain-of-thought
context-engineering
function-calling

// Github Activity

@ave-shina

Followers

Following

Repositories

617

Contributions (past year)

This Week

Best Day

1.7

Daily Avg

SepOctNovDecJanFebMarAprMayJunJulAug

MonWedFri

Less