Anima retweeted
I am not joking when I say this.
Traditional game development is over.
I asked Opus-5.5 to make Attack on Titan in Minecraft. Took ~1hr and cost less than $25 start to finish.
The end result is extremely fun. And multiplayer!
Guide + link to play below.
Traditional game development is over.
I asked Opus-5.5 to make Attack on Titan in Minecraft. Took ~1hr and cost less than $25 start to finish.
The end result is extremely fun. And multiplayer!
Guide + link to play below.
249
435
6,903
425,236
Did someone check if the
"do something GREAT, make sure it's good, double check, make no mistake etc..."
in the prompt actually made the output better, safer... ?
I'm afraid if you don't give specific directions of what you call "beautiful" or "great", it's useless and a waste of token
"do something GREAT, make sure it's good, double check, make no mistake etc..."
in the prompt actually made the output better, safer... ?
I'm afraid if you don't give specific directions of what you call "beautiful" or "great", it's useless and a waste of token
0
0
0
11
OpenAI is adding invisible watermarks to ChatGPT text in the EU.
Funny timing.
The visible watermark has been there for years: the writing itself
+1 billion of people use ChatGPT every week, and the same cadence, phrasing and personality keep showing up everywhere.
I’ve been picker for AI.
Pick Victor Hugo, Camus, De Gaulle, Belmondo...
Download the .md, give it to your AI, then call @VictorHugo whenever you want
Your AI can finally sound like someone.
Coming very soon. DM for early access.
Funny timing.
The visible watermark has been there for years: the writing itself
+1 billion of people use ChatGPT every week, and the same cadence, phrasing and personality keep showing up everywhere.
I’ve been picker for AI.
Pick Victor Hugo, Camus, De Gaulle, Belmondo...
Download the .md, give it to your AI, then call @VictorHugo whenever you want
Your AI can finally sound like someone.
Coming very soon. DM for early access.
We're expanding our approach to content provenance to include text in response to EU regulatory requirements, while recognizing the significant limitations of current text watermarking technology.
Our tools already help verify whether an image or audio file was created with our models. This work builds on those efforts to help people better understand when content may have been generated or edited with an OpenAI model.
In the EU, we’ll start watermarking eligible text from ChatGPT and Codex over the coming weeks to comply with the EU AI Act.
Customers using our API can turn on text watermarking for select models worldwide today.
0
0
0
51
1.2 billion people use ChatGPT every week. And somehow, they’re all starting to sound the same.
The issue is you can spot ChatGPT writing from 300 km away. That’s a problem.
So I built a personality picker for AI.
Choose Victor Hugo, Camus, De Gaulle, Belmondo... Starting with . 🇫🇷🇺🇸
Download the .md, give it to your AI, then call the personality whenever you want with "@ VictorHugo" in your own chats.
You can download several and switch depending on what you're writing.
Coming soon. DM for early access.
The issue is you can spot ChatGPT writing from 300 km away. That’s a problem.
So I built a personality picker for AI.
Choose Victor Hugo, Camus, De Gaulle, Belmondo... Starting with . 🇫🇷🇺🇸
Download the .md, give it to your AI, then call the personality whenever you want with "@ VictorHugo" in your own chats.
You can download several and switch depending on what you're writing.
Coming soon. DM for early access.
0
0
0
57
