News for hackers. Stuff that matters.

smilingemoji

Re:Major Outage Across ChatGPT and API on Thursday November 09, 2023 @04:03PM (#38211259)
This is false equivalence because machines ingest copyrighted material at a different order of magnitude.

Wikipedia has a nice example of an oil stain vs. oil spill. https://en.wikipedia.org/wiki/False_equivalence

You must be joking. Hacker News only has one theme, yet it doesn't stop you from using the site.
Re:Tracking SQLite Database Changes in Git on Thursday November 02, 2023 @09:30AM (#38113258)
Seems a bit over the top when you could also just provide it as a command line argument to sqlite3 which is much more obvious than <<< and works in every shell.

  sqlite3 db.sqlite3 .dump
Re:Tracking SQLite Database Changes in Git on Thursday November 02, 2023 @06:23AM (#38111385)
I love these sort of articles. No new tools are needed here, it shows you how to get the most out of the tools you already know and use. Awesome!
Re:All of ChatGPT's System Prompts on Sunday October 15, 2023 @02:45AM (#37887492)
It still doesn't know about anything that happened in March 2023. It hallucinates instead of saying outright that it doesn't know.

Example: "Many countries had significant political events, whether they were elections, policy changes, or other notable occurrences."

> I really wish people would just stop posting submissions to twitter at this point.

I fully agree. You can also replace twitter.com with nitter.net

https://nitter.net/bagder/status/1709103920914526525?s=46

  The following example code is a bit hard to read:

  const { status } = await send(capitalize(greeting) + "!")
  console.log(status)
I disagree, I find this example code very easy to read because it reads like idiomatic Javascript. Unlike this library.
Re:Show HN: Magentic – Use LLMs as simple Python functions on Tuesday September 26, 2023 @03:47PM (#37664889)
The API looks very clean. Today I learned about "..." in Python
Re:Comparing 60 LLMs with a set of 20 prompts on Saturday September 09, 2023 @11:16AM (#37446353)
I took at the look at the SVG smilies, only GPT gets it right (https://benchmarks.llmonitor.com/svg). You can preview the SVGs drawn by the LLMs by pasting this into the browser console

document.querySelectorAll("td pre").forEach((node) => { let code = node.textContent; node.insertAdjacentHTML('afterend', code) })

Or take a look at my screenshot: https://i.ibb.co/Kw0kp58/Screenshot-2023-09-09-at-17-15-20-h...