News:

BB code in posts seems to be working again!
I haven't turned on every single tag, so please let me know if there are any that are used/needed but not activated.

Main Menu

Artificial intelligence and Viso

Started by Yacine, July 06, 2024, 11:43:20 AM

Previous topic - Next topic

0 Members and 1 Guest are viewing this topic.

Yacine

Hi guys,
We've all had a good laugh at AI's performance and its inability to provide meaningful responses to our questions.

While that may have been true for Gemini and ChatGPT, there's a new player in the field: Claude.ai.
I'm almost tempted not to tell you about it, lest you clutter it with your chats and limit its time for me!

Joking aside:
  • Claude isn't infallible, but it's clever enough to guide you through the intricacies, pitfalls, and solutions of your project change requests.
  • I'm currently working on refactoring projects that other AI assistants deemed impossible.
I can now confidently say that AI is ready to help us Visioneers.

Looking forward to hearing your comments.
Yacine

Visisthebest

I use Claude 3.5 as well, I must say the free ChatGPT 4o is better at Visio coding makes fewer mistakes. Both still produce nonsense frequently if it is harder than a straightforward question.
Visio 2021 Professional

Yacine

Visisthebest, my Pal,
I can't agree with you.

AI in general is quite astonishing.
Gemini came a little bit later on the dance floor, but did not really manage to catch up.
The initiator, the very first serious player was ChatGPT. But yes, still absolutely astonishing.
But the comes a new player - Claude - that makes its competitors look more the robots that they actually are and gives you a feeling to speak to a human peer.

And this is where it gets dangerous, namely forgetting that a very smart and intelligent AI is still a robot. But that is what Claude tries to do.

I will not blame it for that try. It is up to me to stay alert and remember in what context I am.

And I did also notice, that if you throw all too vague requests, you earn "lazy" answers.

The difference is probably that you can work out with it, what it really knows and what it guessed. Unlike ChatGPT it wont trick you by overwhelming you with too long explanations and codes, but rather listen, adjust itself and respond as you ask it for.

I am absolutely not categorical on my statements. Not at all, I am also in an invenstigation phase. This just happens to be my current conclusion.

Eager to hear yours and those of the other peers, comments and opinions.

Regards,
Yacine 
Yacine

Browser ID: smf (possibly_robot)
Templates: 4: index (default), Display (default), GenericControls (default), GenericControls (default).
Sub templates: 6: init, html_above, body_above, main, body_below, html_below.
Language files: 4: index+Modifications.english (default), Post.english (default), Editor.english (default), Drafts.english (default).
Style sheets: 4: index.css, attachments.css, jquery.sceditor.css, responsive.css.
Hooks called: 186 (show)
Files included: 34 - 1306KB. (show)
Memory used: 1090KB.
Tokens: post-login.
Cache hits: 13: 0.00177s for 26,720 bytes (show)
Cache misses: 3: (show)
Queries used: 17.

[Show Queries]