René's URL Explorer Experiment


Title: Mini LLM in Ruby - Runnable Code Snippet

Open Graph Title: Mini LLM in Ruby - Runnable Code Snippet

X Title: Mini LLM in Ruby - Runnable Code Snippet

Description: Demonstrate the core mechanism behind LLMs by predicting the next token, appending it, and repeating. Runnable Ruby snippet with live execution.

Open Graph Description: Demonstrate the core mechanism behind LLMs by predicting the next token, appending it, and repeating. Runnable Ruby snippet with live execution.

X Description: Demonstrate the core mechanism behind LLMs by predicting the next token, appending it, and repeating. Runnable Ruby snippet with live execution.

Keywords:

Opengraph URL: https://tempercode.dev/snippets/mini-llm-ruby

direct link

Domain: tempercode.dev


Hey, it has json ld scripts:
{"@context":"https://schema.org","@type":"SoftwareSourceCode","name":"Mini LLM","description":"Demonstrate the core mechanism behind LLMs by predicting the next token, appending it, and repeating.","programmingLanguage":"Ruby","text":"# LLM is a next-token predictor. That's the whole trick.\n# It looks at text, predicts what comes next, appends it, and repeats.\n\n# These patterns simulate what a model \"learned\" from training.\n# Real LLM learned from trillions of words - same idea, bigger scale.\nlearned = {\n  'hel' => {'l' => 0.9},\n  'ell' => {'o' => 0.9},\n  'llo' => {' ' => 0.6, '!' => 0.3},\n  'lo ' => {'w' => 0.5, 't' => 0.3},\n  'o w' => {'o' => 0.8},\n  ' wo' => {'r' => 0.9},\n  'wor' => {'l' => 0.7},\n  'orl' => {'d' => 0.9},\n  'the' => {' ' => 0.9},\n  'he ' => {'c' => 0.4},\n  'e c' => {'a' => 0.8},\n  ' ca' => {'t' => 0.7},\n  'cat' => {' ' => 0.6, 's' => 0.3},\n  'at ' => {'s' => 0.5},\n  't s' => {'a' => 0.6},\n  ' sa' => {'t' => 0.7},\n}\n\ntext = prompt.downcase\nsteps = [\"Generating from \\\"#{text}\\\":\"]\n\n# Generate up to 12 more characters\n12.times do\n  break if text.length >= 20\n  context = text[-3..-1]\n  probs = learned[context]\n\n  break unless probs  # Unknown pattern\n\n  # Pick highest probability (greedy decoding)\n  next_char, prob = probs.max_by { |_, v| v }\n  steps << \"  \\\"#{context}\\\" → \\\"#{next_char}\\\" (#{(prob * 100).to_i}%)\"\n  text += next_char\nend\n\nsteps << \"Result: \\\"#{text}\\\"\"\nreturn steps.join(\"\\n\")"}

theme-color#0c0d12
color-schemedark
authorTemper
creatorTemper
publisherTemper
og:imagehttps://tempercode.dev/og-image.png
og:typearticle
twitter:cardsummary_large_image
twitter:imagehttps://tempercode.dev/og-image.png

Links:

Temperhttps://tempercode.dev/snippets
Snippetshttps://tempercode.dev/snippets
Editorhttps://tempercode.dev/editor
CLIhttps://tempercode.dev/cli
https://github.com/handcraftbyte/temper-snippets
Snippetshttps://tempercode.dev/snippets
Editorhttps://tempercode.dev/editor
CLIhttps://tempercode.dev/cli
https://github.com/handcraftbyte/temper-snippets/blob/main/algorithms/mini-llm-ruby.md
JavaScripthttps://tempercode.dev/snippets/mini-llm-javascript
Pythonhttps://tempercode.dev/snippets/mini-llm-python
PHPhttps://tempercode.dev/snippets/mini-llm-php
Array DifferenceFind elements in the first array that are not present in the second array.https://tempercode.dev/snippets/array-difference-ruby
Array FrequenciesCount how many times each value appears in an array and return a frequency map.https://tempercode.dev/snippets/array-frequencies-ruby
Array HeadGet the first n elements of an array.https://tempercode.dev/snippets/array-head-ruby
Array IntersectionFind common elements that exist in both arrays.https://tempercode.dev/snippets/array-intersection-ruby
Array TailGet the last n elements of an array.https://tempercode.dev/snippets/array-tail-ruby
Array UnionCombine two arrays and remove duplicates to produce a union.https://tempercode.dev/snippets/array-union-ruby

Viewport: width=device-width, initial-scale=1


URLs of crawlers that visited me.