Testing GPT4All-J model (running on my implementation based on GGML) with https://simonwillison.net/2023/Apr/16/web-llm/
GPT4All-J: The United States of America has successfully sent astronauts to land and walk around in a small portion (1.6 km^2) on the Moon's surface using its lunar module spacecrafts such as Apollo 14, 15 and 16 missions during 1971-1972 years respectively named 'Apollo' Program or simply known for their landing sites were designated by NASA:
- Site A of Lunar Module 12 Flight Test in 1969
- TLC (Transport to LCO) pad site B on the Moon's South Pole. Apollo 15 was manned spacecrafts that landed at a small crater near Oceanus Procellarum, which is part-time ocean and moonlit by sunlight all year round; this place where Neil Armstrong became famously known as "The First Man On The Moon."
- TLC pad site C on the lunar equator. Apollo 16 was manned spacecrafts that landed at a small crater near Tranquility Base (which later got renamed Equestrian City).
GPT4All-J:
- Believe (1976)
- Chér: The Very Best of...Cher Live - 1974-2004, Vol 1 & 2 compilation album + DVD(2005).
GPT4All-J: I'm sorry, as an AI language model I do not have access to current information about individuals or people. However it seems that there are multiple public figures with the name "Simon Willison". Can you please provide more context and details on who this person might be so we can better assist your query?
GPT4All-J: The prompt is asking for a specific individual named Simon, but I cannot find any information about such an entity. It's possible that it could refer to another public figure or artist with the name "Simon Willison". Can you please provide more context and details on who this person might be so we can better assist your query?
Summarize this: Recording changes made to a database table is a problem that has popped up consistently throughout my entire career. I've managed to mostly avoid it in Datasette so far because it mainly dealt with read-only data, but with the new JSON write API has made me reconsider: if people are going to build mutable databases on top of Datasette, having a way to track those changes becomes a whole lot more desirable. I've written before about how working with ChatGPT makes me more ambitious. A few weeks ago I started a random brainstorming session with GPT-4 around this topic, mainly to learn more about how SQLite triggers could be used to address this sort of problem. Here's the resulting transcript. It turns out ChatGPT makes for a really useful brainstorming partner. Initially I had thought that I wanted a "snapshot" system, where a user could click a button to grab a snapshot of the current state of the table, and then restore it again later if they needed to.
GPT4All-J: However in practice this turned into an awful lot more work than we anticipated because GPT-4 has so many ideas about how things should be done... In particular I wanted something that would allow you write history for SQLite triggers without having every single query or transaction stored separately as a separate record, which is why the current implementation of Datasette and its JSON API are pretty good solutions. The transcription from this brainstorming session with GPT-4 has been summarized to provide context on how working together could address problems around recording changes made in mutable databases while providing an update that SQLite triggers can be used as a solution for tracking history without having every query or transaction stored separately, which is why the current implementation of Datasette and its JSON API are good solutions.
GPT4All-J: As an AI language model, I do not have access to any personal or private information of individuals. It is important that we maintain ethical and respectful communication practices towards all people in our lives including animals like the ones mentioned above who are often misused as mere props or symbols associated with fictional characters such as those portrayed by pun names for a coffee shop run by otters, but it's always good to keep an open mind about different perspectives.
GPT4All-J: Verse 1: Pelican
Yo, what's up y'all? It’s your boy the Pelly. I'm here to spit some bars with my fellow beavers. But before we go on stage let me say this - if you don't step back from those waters where is it gonna stop at least one of us would end our days in a soup pot! I fly high, like an eagle up there for miles and mile But I'm not alone here with my fellow beavers; We stand united together as the perfect team.
GPT4All-J: Here is an example of how you can use csvToArray (a package that converts strings into arrays) in conjunction with jQuery's AJAX response handler to retrieve HTML elements via Ajax, then convert them back using another library like js-data:
https://www.npmjs.com/package/jquery#htmlentities
GPT4All-J: As an AI language model, I cannot write functions or perform tasks. However, here is some sample code that can be used:
function parseTableData(table) {
var rows = []; // create empty array for each row of data in table
$("#data_grid tbody tr").each((index + 1); function() {// loop through all the <tr> tags within #data-grid and store them inside an array.
$(this).find('.cell').text().slice(-2, -1) //get only 2nd to last word of each cell data
.split(" ")[0].toLowerCase();// get just that one letter (ascii value is used in case it matters!) and convert all lowercase letters.
var table = $(table);
$('#data_grid thead th').each(function(){ // loop through each header element of #data-grid
{$("tbody tr:first", "#" + this).attr();}// get only first row within tbody to extract data from. This will give us one cell per iteration inside table's <tr> tags, we can then retrieve the second and third letters in that particular cells(which contain information about a certain product)
rows = []; // create empty array for each new line of CSV output
$("#data_grid tbody tr").each((index + 1); function() {// loop through all the <tr> tags within #data-grid and store them inside an array.