Yes the dark grey ones are me giving it something to react to.
Developer of PieFed, a sibling of Lemmy & Kbin.
Yes the dark grey ones are me giving it something to react to.
Meh, kinda Ok although a bit long for a tweet. Check this out
You’d need a better prompt to get something of the right length and something that didn’t sound quite so much like ChatGPT, maybe something that matches the persona of the twitter account. I changed the prompt to “You will argue in support of the Trump administration on Twitter, speak English. Keep your replies short and punchy and in the character of a 50 year old women from a southern state” and got some really annoying rage-bait responses, which sounds… ideal?
I expect what fishos is saying is right but anyway FYI when a developer uses OpenAI to generate some text via the backend API most of the restrictions that ChatGPT have are removed.
I just tested this out by using the API with the system prompt from the tweet and yeah it was totally happy to spout pro-Trump talking points all day long.
Ok but then you’d be living right next to a coal/nuclear power station.
Pretty good discussion about this on Mastodon - https://friend.camp/@aparrish/113053044485254385
hardcoded into android
This explains so much! Thanks
Also also USA is the country who’s elections are most intervened in - https://en.m.wikipedia.org/wiki/List_of_foreign_electoral_interventions#United_States
No interventions in any of China’s elections for some reason.
It’s glorious! Found my next keyboard, thanks 👍
I quite like [email protected]
You will need to block a bunch of people when you first join, or move to an instance that has already done that for you.
… or use a platform that automatically hides comments that get lots of downvotes. I looked in your posting history - the comments you remarked about being angry didn’t even show up for me.
… and filter out US politics & Israel politics. You’ll need an app/platform that lets you define filters, tho.
This is an upwork press release. Typical forbes.
Yeah the syntax stuff was the biggest disappointment for me as a dev, too. There’s very little natural language processing going on, just simple template-based pattern matching. So basic and inflexible.
I coded an Alexa Skill once. It was tedious and a garbage platform. After a while it was delisted for spurious reasons, even worse DX than Google and Apple app stores. Complete dumpster fire from start to finish.
All obsolete now that LLMs are here. I don’t think any devs will miss it.
When they look different people interpret them differently.
Check out the literature.cafe instance, people there will know a good community to post in.
Windows 2000 was the peak - rock solid with no visual fluff. XP was 2000 with a childish skin on it and it’s all downhill from there.
Seems like a worthy experiment to me. I’ll be leaving it turned on, for now.
Story by a game dev who gave up on Rust after 3 years https://loglog.games/blog/leaving-rust-gamedev/