sansxel
sansxel
The AI workshop for makers
ProductLearnPricingContact
sansxelsansxel

The adaptive AI platform. One AI, infinite shapes, a contextual interface that reshapes itself around how you actually work.

Product
ProductLearnPricingDownload
Account
DashboardDownloadUpdatesIntegrationsUsage
Company
PrivacyTermsContact
Community
Discord
© 2026 sansxel. All rights reserved.
All articles
Topics
AI11
ConceptsHow it worksVoiceVision
Coding5
Databases1
APIs3
MCP1
Systems4
Build1
Skills2
Monetization3
Learn/AI

AI

What AI actually is, how it works, what it can and can't do.

Concepts

See all →
beginner4 min

What is AI, really?

AI like ChatGPT works by predicting the next word, kind of like autocomplete, but way smarter. Here's the plain-English version of what's happening under the hood.

Voice

See all →
beginner5 min

How voice AI works (talk → text → AI → speech)

When you talk to an AI, three different models are running in sequence. Here's what each one does and why latency matters more than you think.

Other

New9 min

What is reinforcement learning from human feedback?

A plain-English tour of RLHF: how human preferences get baked into a reward model, why it matters for LLMs, and the open questions about whose values end up encoded.

New9 min

What is computer vision?

A friendly tour of computer vision: what it actually does, how it pulls meaning out of pixels, and where you'll find it showing up in the wild.

New9 min

What is speech recognition?

A friendly tour of how machines turn spoken words into text, why it's harder than it looks, and where the field is heading with self-supervised learning.

New9 min

What is prompt engineering?

A practical look at how natural language became a programming interface, why it's harder than it sounds, and what separates a good prompt from a lucky one.

New8 min

What is retrieval-augmented generation?

RAG lets language models pull in outside information before answering, so they can work with fresh data, internal docs, or knowledge they were never trained on.

New3 min

Large Language Model

A quick reference on what LLMs are, how they're trained and tuned, and how we measure whether they're any good.

New9 min

What is fine-tuning?

Fine-tuning takes a model that already knows something useful and nudges it toward a narrower job. Here's how it actually works, and why it became the default way to ship AI features.

New3 min

Transformer (machine learning model)

A short reference on what a transformer is, how attention works, and why this architecture became the backbone of modern AI.

New8 min

What are embeddings?

Embeddings turn words into vectors that capture meaning. Here's how they work, why they matter, and where they show up in real systems.