[burtonator]

We're stuck here for a while due to the size, and cost, of the larger models.

The main reason I want a non-cloud LLM is that I want one that's unaligned.

I know I'm not a criminal and I want to stop being reprimanded by GPT4.

What I'm most interested here is fine tuning the model with my own content.

That could be super valuable especially if we could get it to fact check itself, which you could with a vector database.

[shostack]

What's been so interesting with the explosion of this has been how prominently the corporately-driven restrictions have been highlighted in news and such.

People are getting a good look in very easy to understand terms at the foundational stage at how limiting the future is to have this just be another big tech controlled thing.

[ChatGTP]

Don’t the general populace also have valid concerns about more powerful models and newer architectures being able to do damage ?

[barking_biscuit]

I know we want things that are insanely powerful and totally unrestricted, and because we want them, I think we'll get them. And then I genuinely think this tech is going to end in tears.

[WhiteNoiz3]

They have said that the alignment actually hurts the performance of the models. Plus for creative applications like video games or novels, you need an unaligned model otherwise it just produces "helpful" and nice characters.

[yeck]

The character simulacrum used by an LLM tends to be the result of "system" prompts that set by the service you are using. GPT-N isn't exactly trained to be helpful and nice, but ChatGPT has system prompts describing the character it should be performing as. If you work with just GPT-4, you can get more zany outputs.

That said, OpenAI does use RLHF, which does bias the model away from raw internet madness and something that OpenAI wanted at the time of training. A lot of models haven't gone through rigorous RLHF, though.

As a side note, RLHF might be the best alignment technique we currently have in practice, but it is not decisive. It has been noted in multiple experiments that RLHF can just train a model in how to trick the human reviewer, if tricking is easier in practice than doing a think the human review wanted. So this isn't even really seen as aligning a model by alignment researchers. At least not an approach that can scale with the increasingly intelligence AI models.

[yeck]

Alignment is an unsolved problem. None of the current stronger models are "aligned", just tuned in ways that weight some biases more than others, but even that is dependant of the features of their inputs.