暂无图片
暂无图片
暂无图片
暂无图片
暂无图片
Daniel Flower-DevOps Experiments with AI_.pdf
61
31页
19次
2023-12-12
免费下载
Prepared by: Daniel Flower
Date: 25/11/2023
Time to Experiment
DevOps Experiments
with AI
2
PUBLIC
Introduction
This is a talk about using and coding with Large Language Models.
I believe that these are very powerful, but no one knows their full potential or
how to maximise their use yet.
Therefore, now is a time to try many experiments to see what works.
This talk has a very brief overview of Large Language Models and then just
shows a few experiments.
The intention is give ideas about the kinds of things we can do with it, to inspire
others to start experimenting more.
3
PUBLIC
How they work
Large language models
It takes some words as input. It generates the next word. It repeats this to make sentences and paragraphs.
It remembers nothing. It learns nothing. So we need to give it everything it needs to know as input.
It tries to guess what "sounds" best - not what is true.
it is able to guess based not just on stats, but by generalising, "reasoning", and other things
function guessNextWord( input: words Array<String> ) output: String {
var numbers = convertWordsToNumbers(words);
var nextNumber = guessNextNumber(numbers);
return convertNumberToWord(nextNumber);
}
function guessNextNumber( input: numbers Array<Number> ) output: Number {
if (numbers.size > 8192) throw "Sorry! Too many inputs";
var guess = numbers[0] * 0.123124 + numbers[1] * 0.584935 + ...
// Huge amount of adding and multiplying numbers, but no state nor network calls etc
// Training the model takes a huge amount of time and money
return guess;
}
of 31
免费下载
【版权声明】本文为墨天轮用户原创内容,转载时必须标注文档的来源(墨天轮),文档链接,文档作者等基本信息,否则作者和墨天轮有权追究责任。如果您发现墨天轮中有涉嫌抄袭或者侵权的内容,欢迎发送邮件至:contact@modb.pro进行举报,并提供相关证据,一经查实,墨天轮将立刻删除相关内容。