Re:OpenAI's new open-source model is basically Phi-5
by jofzar on Friday August 08, 2025 @04:55AM
(#44834923)
Sorry just to ask, what kind of job do you have? Sex therapist sounds like the closest?
Re:OpenAI's new open-source model is basically Phi-5
by itsdesmond on Friday August 08, 2025 @05:27AM
(#44835107)
I don’t think they’re using it for work.
Re:OpenAI's new open-source model is basically Phi-5
by wkat4242 on Friday August 08, 2025 @09:41AM
(#44836824)
Correct, I'm just very kinky/bdsm/polyamorous and so are all my friends. I do have a sexuologist though, and I often write stuff up for her when she asks me to. Where the AI also comes in sometimes.
Re:OpenAI's new open-source model is basically Phi-5
by Clueed on Friday August 08, 2025 @05:33AM
(#44835139)
I found DeepSeek R1 (better for questions) and V3 (better for prose) to be very willing to discuss sex with a simple system prompt, as well as being very pleasant in articulation.
I guess, I prefer them because they are almost SOTA and very large.
Not through the official interface though. Needs to be hosted by a third party. OpenRouter has a generous free tier for both.
I just saw that there is an abliterated version as well. Not sure how to try it though.
Re:OpenAI's new open-source model is basically Phi-5
by wkat4242 on Friday August 08, 2025 @09:38AM
(#44836787)
Oh yeah I was mainly thinking about smaller models because I want to run them locally. Not just because of the abliteration. I just want everything personal to run locally only. I don't trust any of the cloud companies.
Re:OpenAI's new open-source model is basically Phi-5
by Havoc on Friday August 08, 2025 @07:22AM
(#44835750)
Pretty sure I saw an uncensored version yesterday on localllama
Re:OpenAI's new open-source model is basically Phi-5
by wkat4242 on Friday August 08, 2025 @09:42AM
(#44836831)
huh interesting thanks! I'll have a look.
Re:OpenAI's new open-source model is basically Phi-5
by Havoc on Friday August 08, 2025 @10:59AM
(#44837809)
Think they call it abliterated not uncensored but same thing from what I understand
Re:OpenAI's new open-source model is basically Phi-5
by wkat4242 on Friday August 08, 2025 @02:07PM
(#44839879)
Yes abliteration is one method of uncensoring models, that's why. I think there's more.
Re:OpenAI's new open-source model is basically Phi-5
by Alex-Programs on Friday August 08, 2025 @07:56AM
(#44835973)
I'm curious whether you can get https://platform.nuenki.app (my deep translation service; I'm just polishing it before release) to run into "too sexual". It's designed to be resilient to that kind of thing, and it works well in my testing, but maybe you have some better "stress test" content than me!
Re:OpenAI's new open-source model is basically Phi-5
by wkat4242 on Friday August 08, 2025 @09:40AM
(#44836810)
I don't use hosted AI much. But one of the reasons I like AI is that I can ask it something like "Hmm I don't like how this sounds, can you formulate it another way, more colloquial?" and it'll take that into account. Or what I often get is that it translates "you" to singular when I need plural and vice versa. In most languages that differs but not in English.
Right now I'm using abliterated llama 3.1 (I have no need for vision) which is perfect.
Until gpt-oss can be abliterated it's no use to me.