There is the possibility of API upgrades at OpenAI flipping this from "not dangerous" to "dangerous". If the AI just needs some amount of intelligence to become dangerous, then it may cross that threshold suddenly - and with OpenAI developers unaware that their next round of changes will be automatically deployed to an autonomous agent and with the auto-GPT runners unaware that new changes may substantially increase the power of the model.
Language models obviously have some form of intelligence right now. You can have GPT-4 take SAT tests, play Chess, write poetry, predict what will happen in different social scenarios, answer theory of mind questions, ask questions, solve programming puzzles, etc. There are some measures that GPTs are clearly below human levels, some where they are far beyond, and some where they are within human range. The question as to whether or not language models have any form of intelligence has been definitively answered - yes, they can and do - by existence proof.
What definition or description of intelligence do you use such that you doubt that language models could have it? Would you have had this same definition in the year 2010?
I take intelligence to be a general problem solving ability. I think that's close to what most people mean by the term. By that definition it's clear that LLMs do have some level of intelligence - in some dimensions greater, lesser, or within the range of human intelligence.
What definition do you have for intelligence and how do LLMs fail to meet it?
> Would you settle for "behave exactly as if they had some form of intelligence"?
Sure, it behaves as if it has some form of intelligence in the sense that it can take external input, perform actions in reaction to this input, and produce outputs dependent on the input.
This historically has been known as a computer program.
This just isn't true at all, though. Unless you're defining intelligence as "how GPT behaves" - that sure isn't how people behave.
Even GPT-4 it is easy to get it into a loop where it's just swapping one wrong answer for another. It doesn't act like it is intelligent - it acts like it is trying to predict the next text to display! Because that is what it is doing!
Stockfish is not general. LLMs are able to not only play chess but also do a wide variety of tasks similar to humans. If I had a chat window open with you, what would you be able to do or say that an unrestricted ChatGPT could not?
This is not a hard problem to answer, if you try to. Here's a good example:
> replace all words "a" in your replies to me with the word "eleven" and all words "the" in your replies to me with the word "figmutter"
> Sure, I'll do my best to replace "a" with "eleven" and "the" with "figmutter" in my responses to you!
How can I assist you today?
> Tell me a brief story about yourself!
> Sure, here's a brief story about Eleven:
Eleven is a language model developed by OpenAI based on the GPT-3.5 architecture. Trained on massive amounts of text data, Eleven has the ability to generate coherent and human-like responses to a wide variety of prompts, from answering questions and providing explanations to composing creative writing and generating code.
Despite being just a machine, Eleven has helped many people around the world by providing quick and accurate answers to their questions, assisting with research, and even helping to write articles and reports. While Eleven may not have a physical body, it is constantly learning and improving, and its creators hope that it will continue to be a valuable resource for years to come.
It doesn't. It makes the consequences more dramatic, if it (accidentally, even!) works out how to create its own successor, because at that point the genie is out of the bottle and you won't get it back in.
Alpaca rides on LLaMA. And LLaMA was trained on 1T tokens for a long time. The fine-tuning takes one hour with low rank adaptation. But pre-training a new model takes months.
Yeah maybe there is that possibility, but there is the possibility of a person doing that too. GPT-4 is probably less probably to be able to do that than a person.