Saemal (working title) — from thought to code, from intent to action

We are building a programming language written in Hangul to lower the barriers to programming and expand what people can express.

Just as Hunminjeongeum was created so that anyone could express themselves, this language aims to let anyone learn quickly and turn ideas into code. The language takes on complexity such as Rust-style ownership and C-style manual memory management, so people can focus on what they want to build. It is designed for people and AI to code together, and it is under development and not yet released.

Code written in this language: the same average, two ways

Step by step

1점수들 = [80, 90, 75, 95]2합계 = 03점수들.각각 처리 |점수|4  합계 += 점수5끝6출력 합계 / (점수들.길이 * 1.0)

One line with the built-in

1점수들 = [80, 90, 75, 95]2출력 점수들.평균

Output of both: 85.0

"Saemal" is a working title, not the official name. The official name will be announced at release.

What would you like it to make easy? (select any)

Probability & statistics practice

Machine learning & LLM practice

Learning to code

Data analysis & visualization

Web & app development

Automation

Fast programs

Other

Learn the principles behind AI — properly

NumLM explains probability, statistics, machine learning and large language models from first principles — with formulas you can follow, worked examples, and experiments whose results are published as they happen.

Lessons in English

Descriptive Statistics

Coefficient of Variation

The coefficient of variation (CV) is a relative measure of spread equal to the standard deviation divided by the mean; because the units cancel, it is a…

Descriptive Statistics

Skewness

Skewness is a standardized third-moment statistic that measures how far a data distribution departs from left–right symmetry (it is a defined term in the…

Probability Distributions

Poisson Distribution

The Poisson distribution is a discrete probability distribution for the number of rare, independent events that occur in a fixed interval of time or space…

Probability Distributions

Law of Large Numbers

The law of large numbers is a fundamental theorem of probability stating that as the number of independent trials n increases, the sample mean converges to…

Machine Learning

Association Rules and Anomaly Detection

Association rule learning is an unsupervised learning task that finds patterns of items appearing together — such as "customers who buy A also buy B" —…

Probability Distributions

Normal Distribution

The normal distribution is a symmetric, bell-shaped continuous probability distribution centered on its mean μ, with probability density function f(x) =…

Probability Distributions

Central Limit Theorem

The central limit theorem (CLT) states that when independent samples of sufficiently large size n are drawn from a population with mean μ and variance σ²,…

Probability

Bayes' Theorem: The Core Idea

Bayes' theorem is the conditional-probability rule P(A|B) = P(B|A)P(A)/P(B), which tells you how to update a prior probability P(A) into a posterior…

inference

The p-Value

A p-value is the probability, assuming the null hypothesis is true, of obtaining a test statistic at least as extreme as the one observed; it ranges from 0…

Inferential Statistics

Confidence Interval

A confidence interval is an interval estimate constructed so that, if the same sampling procedure were repeated many times, a specified proportion of the…

Public experiment

Can AI predict lottery numbers?

Statistical, LSTM, Transformer and ensemble models each publish 100 combinations before every Korean Lotto 6/45 draw. After the draw they are scored against random picks and the theoretical baseline — and the cumulative record is never edited.

See the results

Everything else is in Korean

The full curriculum — hundreds of concept pages and 46 interactive labs — is written in Korean. Your browser can translate it: in Chrome, right-click the page and choose “Translate to English”. We add English pages based on what readers actually use.

한국어 사이트로 가기 (Korean site) →