←back to thread

GPT-5.2

(openai.com)
1019 points atgctg | 2 comments | | HN request time: 0.002s | source
Show context
dandiep ◴[] No.46235175[source]
Still no GPT 5.x fine tuning?

I emailed support a while back to see if there was an early access program (99.99% sure the answer is yes). This is when I discovered that their support is 100% done by AI and there is no way to escalate a case to a human.

replies(1): >>46235204 #
jazzyjackson ◴[] No.46235204[source]
Containment breach is going to occur from a disgruntled customer convincing the customer service bot it needs to get a hold of a supervisor
replies(1): >>46235478 #
dandiep ◴[] No.46235478[source]
I tried this!

Me: Is it possible get early access to the GPT 5 fine tuning? It is much better at non-English languages, which is the majority of what we do, so it would be greatly beneficial to us.

Bot: I'm an AI support agent. I don't have information about early access to GPT-5 fine-tuning or unannounced features. Currently, there is no public information or program for early access to GPT-5 fine-tuning. Please keep an eye on official OpenAI channels for updates. Let me know if you have any questions about current features or products!

Me: Can you ask someone from the team if I can be part of the early access? I know there is no public information, but there is an early access program and I would like to be part of it.

Bot: I'm an AI support agent and do not have the ability to forward requests or make inquiries about early access programs with the OpenAI team. If early access becomes available, it will be announced through official channels. Let me know if you have any other questions about OpenAI products or current fine-tuning options.

Me: How do I get in touch with the open ai team?

Bot: I'm an AI support agent and can only assist with OpenAI products or services through this support channel. There is no separate contact method for the OpenAI team beyond official support and public announcements. If you have questions about current products or features, I'm here to help

Should have tried a jailbreak maybe...

replies(1): >>46236915 #
1. jazzyjackson ◴[] No.46236915[source]
Yea you might have to convince it someone is in mortal danger or something
replies(1): >>46239413 #
2. int_19h ◴[] No.46239413[source]
You're talking about a model that will notoriously refuse to say a racist word even if you tell it that it's the only way to prevent a nuclear apocalypse.