<feed xmlns="http://www.w3.org/2005/Atom"> <id>https://huncoding.github.io/</id><title>HunCoding</title><subtitle>O blog oficial do canal HunCoding. Conteúdo sobre programação, tecnologia e projetos.</subtitle> <updated>2026-05-04T20:33:50-03:00</updated> <author> <name>Otavio Celestino dos Santos</name> <uri>https://huncoding.github.io/</uri> </author><link rel="self" type="application/atom+xml" href="https://huncoding.github.io/feed.xml"/><link rel="alternate" type="text/html" hreflang="pt-BR" href="https://huncoding.github.io/"/> <generator uri="https://jekyllrb.com/" version="4.4.1">Jekyll</generator> <rights> © 2026 Otavio Celestino dos Santos </rights> <icon>/assets/img/favicons/favicon.ico</icon> <logo>/assets/img/favicons/favicon-96x96.png</logo> <entry><title>LLM from Scratch in Go: How Machines Read Text</title><link href="https://huncoding.github.io/llm-from-scratch-how-machines-read-text-en/" rel="alternate" type="text/html" title="LLM from Scratch in Go: How Machines Read Text" /><published>2026-05-04T08:00:00-03:00</published> <updated>2026-05-04T20:33:30-03:00</updated> <id>https://huncoding.github.io/llm-from-scratch-how-machines-read-text-en/</id> <content type="text/html" src="https://huncoding.github.io/llm-from-scratch-how-machines-read-text-en/" /> <author> <name>otavio_celestino</name> </author> <category term="Go" /> <category term="AI" /> <category term="LLM" /> <category term="Machine Learning" /> <summary>Hey everyone! This is the first post in a series called LLM from Scratch in Go. The goal is straightforward: build a language model from zero, in Go, with no external machine learning libraries. No PyTorch, no HuggingFace, no ready-made wrappers. Just plain Go. The series follows the videos on the channel covering: what is an LLM, how computers represent text, implementing a simple tokenizer,...</summary> </entry> <entry><title>LLM do Zero em Go: como máquinas leem texto</title><link href="https://huncoding.github.io/llm-do-zero-como-maquinas-leem-texto/" rel="alternate" type="text/html" title="LLM do Zero em Go: como máquinas leem texto" /><published>2026-05-04T08:00:00-03:00</published> <updated>2026-05-04T20:33:30-03:00</updated> <id>https://huncoding.github.io/llm-do-zero-como-maquinas-leem-texto/</id> <content type="text/html" src="https://huncoding.github.io/llm-do-zero-como-maquinas-leem-texto/" /> <author> <name>otavio_celestino</name> </author> <category term="Go" /> <category term="IA" /> <category term="LLM" /> <category term="Machine Learning" /> <summary>E aí, pessoal! Esta é a primeira parte de uma série chamada LLM do Zero em Go. A proposta é simples: construir um modelo de linguagem do zero, em Go, sem nenhuma biblioteca externa de machine learning. Nada de PyTorch, nada de HuggingFace, nada de wrappers prontos. Só Go puro. A série acompanha os vídeos do canal que cobrem: o que é um LLM, como o computador representa texto, como implementar...</summary> </entry> <entry><title>Go Survey 2025: Gin Still Leads and more data about the language use</title><link href="https://huncoding.github.io/go-survey-2025-gin-dominates-en/" rel="alternate" type="text/html" title="Go Survey 2025: Gin Still Leads and more data about the language use" /><published>2026-04-28T08:00:00-03:00</published> <updated>2026-05-04T20:33:30-03:00</updated> <id>https://huncoding.github.io/go-survey-2025-gin-dominates-en/</id> <content type="text/html" src="https://huncoding.github.io/go-survey-2025-gin-dominates-en/" /> <author> <name>otavio_celestino</name> </author> <category term="Go" /> <category term="Community" /> <category term="Ecosystem" /> <summary>Hey everyone! In January 2026, the Go Developer Survey 2025 was officially published on the Go blog. In November 2025, JetBrains published their annual Go ecosystem analysis based on GoLand usage data. The two landed within months of each other and together form the most complete picture we have ever had of what Go developers are actually using day to day. The short answer: Gin still leads by...</summary> </entry> <entry><title>Go Survey 2025: Gin ainda domina e mais dados sobre o uso da linguagem</title><link href="https://huncoding.github.io/go-survey-2025-gin-domina/" rel="alternate" type="text/html" title="Go Survey 2025: Gin ainda domina e mais dados sobre o uso da linguagem" /><published>2026-04-28T08:00:00-03:00</published> <updated>2026-05-04T20:33:30-03:00</updated> <id>https://huncoding.github.io/go-survey-2025-gin-domina/</id> <content type="text/html" src="https://huncoding.github.io/go-survey-2025-gin-domina/" /> <author> <name>otavio_celestino</name> </author> <category term="Go" /> <category term="Comunidade" /> <category term="Ecossistema" /> <summary>E aí, pessoal! Em janeiro de 2026, o Go Developer Survey 2025 foi publicado oficialmente no blog do Go. Em novembro de 2025, o JetBrains publicou sua análise anual do ecossistema Go com base nos dados de uso do GoLand. Os dois chegaram num intervalo de meses e, juntos, formam a foto mais completa que já tivemos do que os desenvolvedores Go estão de fato usando no dia a dia. Gin ainda lidera c...</summary> </entry> <entry><title>Attention and the mini LLM generating text</title><link href="https://huncoding.github.io/llm-do-zero-attention-mini-llm-en/" rel="alternate" type="text/html" title="Attention and the mini LLM generating text" /><published>2026-04-27T08:00:00-03:00</published> <updated>2026-05-04T20:33:30-03:00</updated> <id>https://huncoding.github.io/llm-do-zero-attention-mini-llm-en/</id> <content type="text/html" src="https://huncoding.github.io/llm-do-zero-attention-mini-llm-en/" /> <author> <name>otavio_celestino</name> </author> <category term="Go" /> <category term="AI" /> <category term="LLM" /> <summary>Hey everyone! This is the fifth and final post in the LLM from Scratch in Go series. In the previous posts we built a BPE tokenizer (post 1), word vectors with semantic search (post 2), a Markov chain and its limits (post 3), and a feedforward network with manual backpropagation (post 4). This post covers videos 13 to 15 of the series. We have arrived at the central mechanism that separates a...</summary> </entry> </feed>
