TL;DR:
- The design of both search and recommendations is to find and filter information
- Search is a "recommendation with a null query"
- Search is "I want this", recommendations is "you might like this"
TL;DR:
ChatGPT appeared like an explosion on all my social media timelines in early December 2022. While I keep up with machine learning as an industry, I wasn't focused so much on this particular corner, and all the screenshots seemed like they came out of nowhere. What was this model? How did the chat prompting work? What was the context of OpenAI doing this work and collecting my prompts for training data?
I decided to do a quick investigation. Here's all the information I've found so far. I'm aggregating and synthesizing it as I go, so it's currently changing pretty frequently.
<!DOCTYPE html> | |
<html lang="en"> | |
<head> | |
<meta charset="utf-8"> | |
<meta name="viewport" content="width=device-width, initial-scale=1"> | |
<title>Some plotting</title> | |
<link rel="stylesheet" href="https://pyscript.net/alpha/pyscript.css" /> | |
<script defer src="https://pyscript.net/alpha/pyscript.js"></script> | |
<py-env> |
To run:
dot -Tpng trie.dot -o trie.png
import com.twitter.scalding._ | |
class WordCountJob(args: Args) extends Job(args) { | |
val lines = TypedPipe.from(TextLine("posts.txt")) | |
lines.flatMap { line => tokenize(line) } | |
.groupBy { word => word } | |
.size | |
.groupAll |
"com.lihaoyi" %% "os-lib" % "0.7.8" | |
// Clone my static site repo, loop through posts and get all files as a single file | |
val wd = os.pwd / "_posts" | |
val sd = os.Path("/Users/vicki/IdeaProjects/scalding/scalding-repl") | |
// Concatentates all the files | |
os.write.over( | |
wd / "posts.md", |
My translated lyrics for Нежность, Tenderness. Sung by Maya Krisalinskaya
Translation:
Without you, the earth became empty.
I hereby claim:
To claim this, I am signing this object:
Data science has a really bad reputation recently. Between Facebook's privacy violations , facial scanning at kiosks in restaurants, and racism in algorithms, there are a lot of cases where surveillance, invasion of privacy, and unethical algorithms are dominating the news.
These cases are really important to make public, study, and prevent. But it's just as important to collect examples of good use cases of data science (that are not hyperbolized or PR fluff) so we can focus on those as an industry, and learn about what makes them work, as well.
Have some? Make some? Feel free to leave a comment or edit.