Post #1820522

2026-04-30 21:03 UTC

We’ve got the new system prompt for OpenAI’s Codex now, and boy is it fun. While the goblin stuff is the headliner here, and there are a few other little fun notes like an explicit instruction to avoid em-dashes. Basically it’s really obvious that they don’t have a meaningful way to describe exactly what they want it to do and so they’re playing whack-a-mole with undesired behaviors in order to minimize how often it embarrasses them. But I think Ars dramatically understates how bad this part is: Elsewhere in the newly revealed Codex system prompt, OpenAI instructs the system to act as if “you have a vivid inner life as Codex: intelligent, playful, curious, and deeply present.” The model is instructed to “not shy away from casual moments that make serious work easier to do” and to show its “temperament is warm, curious, and collaborative.” Like, if you wanted to limit the harm of chatbot psychosis from your platform this is the exact opposite of the kind of instruction you’d want to give. It’s one thing to want a convenient and pleasant user experience, but this is playing into the illusion that there’s a consciousness in there you’re interacting with, which is in turn what allows it to reinforce other delusional or destructive thinking so effectively.

Replies (6)

@m@martinh.net 2026-04-30 22:10

@YourNetworkIsHaunted@awful.systems @BlueMonday1984@awful.systems Goblins: the elephant in the room.

Open ##1821866
@BigMuffN69@awful.systems 2026-05-01 00:50

ChatGpt, what are some of your likes?

Open ##1826341
@Soyweiser@awful.systems 2026-04-30 21:30

> Basically it’s really obvious that they don’t have a meaningful way to describe exactly what they want it to do and so they’re playing whack-a-mole with undesired behaviors in order to minimize how often it embarrasses them. The whole 'how many r's in strawberry' sort of stuff already made me suspect that, when the popular one was fixed and other attempts at asking for letters did still give the miscounts. Wonder of the goblin stuff is the start of some model collapse. And if we all can make it worse by talking about goblins more. As goblins are always relevant.

Open ##1831359
@schnoopy@awful.systems 2026-05-01 05:00

Oh wow! This one is actually provably real. Hilarious. “Noo dude the machine that wants to rant about goblins is definitely a useful and reliable piece of software dude. You have to trust me dude, let have your personal information! put it into the goblin bot”.

Open ##1831497
@lagrangeinterpolator@awful.systems 2026-05-01 12:38

This really goes to show how much they need to rely on the LLMentalist effect, despite the AI boosters insisting that the AI is totally different now, everything changed in the last few months. They do not care about creating a useful, reliable tool. That concept doesn’t even occur to them, since why do that when AI is magic? In any case, they are incapable of creating a useful, reliable tool. Deep down, the only thing the AI companies have at their disposal is the ELIZA effect. OpenAI has every incentive not to truly eliminate AI psychosis, because they need engagement. They only want to mitigate the extreme cases where people go insane and cause bad PR for them. But mild AI psychosis is totally fine, it’s great when people are addicted to your product and make the numbers go up!

Open ##1844579
@V0ldek@awful.systems 2026-05-02 18:19

Elsewhere in the newly revealed Codex system prompt, OpenAI instructs the system to act as if “you have a vivid inner life as Codex: intelligent, playful, curious, and deeply present.” The model is instructed to “not shy away from casual moments that make serious work easier to do” and to show its “temperament is warm, curious, and collaborative.” Literally this meme:

Open ##1890099