The encyclopedia of artificial intelligence

Understand AI.

4,512 articles100 categories

Explore the encyclopedia, compare models, and build practical skills.

Explore all learning paths

Worth exploring

An in-depth explainer and new additions to the encyclopedia.

Browse topics

New to the wiki

Multiple sequence alignment

A multiple sequence alignment (MSA) arranges three or more biological sequences, usually proteins, DNA or RNA, in a grid so that residues placed in the same column are treated as descendants of the same position in a common ancestor.

Fact-checked Sep 11, 2026
40 new articles since Sep 5

Put AI knowledge to work

All tools

Recently revised

Explore an updated article and check its review status.

All recent changes
  • DeepSeek V3.2

    DeepSeek-V3.2 is an open-weight Mixture of Experts large language model family developed by DeepSeek that introduces DeepSeek Sparse Attention (DSA)

    Fact-checked Sep 11, 2026
  • Multi-head Latent Attention

    Multi-head Latent Attention (MLA) is an attention mechanism for transformer models that achieves a 93.3% reduction in key-value cache size while maintaining or exceeding the performance of traditional multi-head attention.

    Fact-checked Sep 11, 2026
  • GPT-Realtime / OpenAI Realtime API

    GPT-Realtime is a family of speech-to-speech models exposed through the OpenAI Realtime API, a low-latency interface that lets developers build voice agents which take spoken audio in and return spoken audio out without an intermediate text transcription…

    Fact-checked Sep 11, 2026

Provider status

Checking official OpenAI and Claude status sources.

Checking now

All provider status →

How this encyclopedia is checked

Help improve AI WikiSuggest a correction, add a source, or research a missing topic.

Help build AI Wiki

Fix one fact, add a source, or propose a missing article.

How to contribute →
Found something inaccurate? Review corrections or use the report button on any article.

Repositories to research

No matching article was recorded when these repositories were detected. Open the original repository and search the wiki before proposing a page.

How to propose an article