Quantcast
Channel: The lost outpost
Viewing all articles
Browse latest Browse all 138

AI-ngels and Demons

$
0
0

Yesterday I came across two fun and interesting uses of large language models, in quick succession.

First, I saw a post on Mastodon commenting about how “brutal” a web app called GitHub Roaster is, in analysing a user’s profile and repository history. That’s a very accurate assessment. The app uses OpenAI’s GPT-4o to create “a short and harsh roasting” for a given profile. The result for my profile was sufficiently uncomfortable to read, that I swiftly moved on!

Very soon afterwards, my friend Tim Kellogg replied to my boost of the original Mastodon post to point out another app, which takes a different angle. Praise my GitHub Profile has a fantastic strapline:

Instead of trying to tear each other down with AI, why not use it to help lift others up?

I love this approach!

A screenshot from Praise my GitHub profile! for the user andypiper.

Text reads:

"Andy, it's amazing to see how much you're accomplishing and the various communities you're a part of. Your dedication to community, code, and respect shines through in everything you do.
Your work with Mastodon, OpenUK, and Makeroni is truly inspiring, and your passion for making things happen is contagious. Whether you're
helping others or creating something new, you always seem to approach it with enthusiasm and kindness.
I love how you've curated a collection of platforms where people can find you, from Glitch to GitLab, and even RoutineHub for Apple Shortcuts! It's a testament to your creativity and willingness to experiment with different tools and technologies.
Your "Fun Facts" section is also a great reminder that it's okay to have fun and not take ourselves too seriously. Who wouldn't want to learn MicroPython or dig out an old Acorn Risc PC from the cobwebs?
As someone who clearly values community and connection, I'm sure you're making a positive impact on everyone around you. Keep being your awesome self, Andy!
(Also, don't forget to send out that newsletter)"

(from a technical perspective, I noted that this app uses the prompt “give uplifting words of encouragement” with LLaMa 3.1 70b, to create more positive output)

If we’re going to use these sorts of tools and make these kinds of apps – let’s do so in a positive manner. Notwithstanding the very real issues with the overuse of resources, and the moral and legal debates around how the models have been trained – both of which I have huge concerns about – I strongly believe that technology has the capacity to have a positive impact on society when used well, ethically, and thoughtfully. Like everything else though, it is up to us to make the best, and most positive use of what we have access to, what we create, and what we leave behind in the world. It is our individual, and our collective, responsibility.

Thank you, Xe, for being thoughtful about this. You’re inspiring!


Viewing all articles
Browse latest Browse all 138

Trending Articles