Readit NewsSo far it's just reinforcing my feeling that none of this is actually used at scale.. We use AI as relatively dumb companions, let them go wilder on side projects which have loser constraints, and Agent are pure hype (or for very niche use cases)
Luc Julia (one of the main Siri's creators) describe a very similar exercice in this interview [0](It's in french, although the au translation isn't too bad)
The gist of it, is that he describes this exercice he does with his students, where they ask chatgpt about Victor Hugo's biography, and then proceed to spot the errors made by Chatgtp.
This setup is simple, but there are very interesting mechanisms in place. The student get to learn about challenging facts, do fact checking, cross reference, etc. While also asserting the reference figure of the teacher, with the knowledge to take down chat gpt.
Well done :)
Edit: adding link
[0] https://youtube.com/shorts/SlyUvvbzRPc?si=2Fv-KIgls-uxr_3z
Searching for this post, I ended up scrolling through the HN result of "new York rats" [1]. It paints quite a story! Couldn't imagine it was such an intense topic (running for more than a decade!)
I'm surprised it hasn't been raised when talking about saving 2Tb/year only for React. It represents costs, which doesn't seem to be an issue, but also computing power and storage. (Event with a higher/longer computing power due to slower compression, it's done once per version, which isn't really comprable to the amount of downloads anyway)
Hard to calculate the exact saving, but it would represent a smaller CO2 footprint..
Here the scale of time is larger and does make the 5$ significant, while it isn't at the scale of a few days.
And what's that about notes taking 120 Mb, when Electron apps start at 3-400 Mb? Deceptively split into <App Name> and <App Name Helper (Renderer).
Not to mention when you leave a chat app like Discord or Slack running and they keep instatiating those meme gifs forever, until you run out of ram.
- making sure it works on all platforms independently of the browser you use (because it comes packages with chromium)
- having access to more API from the platform. Although the UI is rendered through a WebView, there's still native code running, that you can hook back into your app. That can be useful to either offload some logic to native, or access native API that you pilot from the WebApps
- having a shortcut icon to open you app in the system (although this is getting obsolete now that Chrome and Safari offer "Add to Desktop" functionally)
I mean, in the context of JS 10 years ago, Typescript in indeed overly complex, but in the context of today's JS running servers and very complex apps at scale, it just seems sane to back up the code with types, just as most other languages would do..
In my opinion it's now a required complexity to build up a lib with some stability and a safe DX for contributors
Depends on what is considered as small enough for the LLM to be resolved with a high confidence.