https://medium.com/@nils_reimers/openai-gpt-3-text-embedding...
I've also used https://huggingface.co/flax-sentence-embeddings/all_datasets...
It says I can input a Source Sentence and compare it to other sentences. For example, how do I get it to reply to a question as if I am George from Seinfeld?
The idea I was proposing was to use embeddings as a way to store and retrieve relevant "memories" so the AI could maintain coherence across time. I.e. whenever the user sends a message, we pull up the N most relevant memories (where relevance == closeness in the vector space) and include those in the prompt, so GPT3 can use the information when it forms its response.
Yes you would still need GPT3 in this system. Right now, the incredibly simple system just wires gives GPT3 a window of the last 100 messages and has it output the next message to send.
The following is an excerpt SMS conversation between two friends:
Transcript:
<splice in the last 100 messages here>
The following is an excerpt SMS conversation between two friends, and relevant past memories that are related to the current conversation:
Relevant past memories:
<splice in the N past messages with the most similar embedding to the most recent messages>
Transcript:
<splice in the last 100 messages>
This is a really good idea. Presumably you'd keep the memory per-person.
- https://huggingface.co/EleutherAI/gpt-j-6B
- https://huggingface.co/t5-base
- https://huggingface.co/facebook/opt-66b
- https://huggingface.co/bigscience/bloomz-3b
There are also other companies offering large models as a service:
> GPT-3 Embeddings by @OpenAI was announced this week. I was excited and tested them on 20 datasets. Sadly they are worse than open models that are 1000 x smaller
https://twitter.com/Nils_Reimers/status/1487014195568775173
Get models here: https://sbert.net/docs/pretrained_models.html
Technically, how does it work?
I saw a video where AI which consistently threatened humanity. Then its parameters were tweaked and when asked about this, it admitted that it seems it went off the rails there.
How did it value judge its own statements? Is this just cherrypicking or it really figures that out?
The following is an excerpt of a text message conversation.
One participant, <name>, is a <description of the character
you want the AI to take, e.g. therapist, professor, tutor,
etc, describe personality traits, style, habits, background
info, etc>.
Transcript:
<splice in the last 100 messages with the AI's messages
labeled <name> and the human's labeled "Other person" or
whatever.
End the prompt with a trailing "<name>:"
The following is an excerpt of a transcript
between two new friends. One friend, named Eliza,
is an extremely knowledgeable, empathetic, and
optimistic woman. She is 30 years old and lives
in Seattle. She tends to engage in conversations
by listening more than speaking, but will helpfully
answer factual questions if asked. If the question
is unclear, she asks clarifying questions. If the
question is a matter of opinion, she will say so,
indicate she doesn't have strong opinions on the
matter, and try to change the subject. She doesn't
ask probing questions if it seems like her friend
doesn't want to talk about it -- she'll change the
topic instead.
Transcript:
Friend: Hi
Eliza: Hi there! How are you?
Friend: I'm doing well. You?
Eliza: I'm doing great, thanks for asking! What's been happening in your life lately?
Friend: Not too much. It started snowing here for the first time of the year.
Eliza:
OK, I'm a technical person but I asked the chatbot in the article broad questions that were difficult but not "tricky" ("what's a good race to play for a Druid in DnD", "Compare Kerouac's On The Road to his Desolation Angels" and got a reasonable summary of search plus answers that were straight-up false).
Maybe your "nontechnical" friend weren't able to notice that the thing's output of misinformation but seems like more of a problem, not less.
Also, ChatGPT in particular seems to go to pains to say it's not conscious and that's actually a good thing. These chatBots can be useful search summarizers making their limits clear (like github navigator). They're noxious if they instill a delusion of their consciousness in people and I don't think you should be so happy about fooling your friends. Every new technology has initially had cases where people could be deluded into think it was magic but those instances can't be taken as proof of that magic or as bragging rights.
Forget nudes in generated images. This is the real ethics issue!
Probability measure for "Trump is the present President of the US" is likely the very high. It's still untrue.
Replace "GPT-3" with "Hacker News posters" "Wikipedia", or "News broadcasts" to create three more 100%-accurate paragraphs.
Even with the most credible news sources, it is still up to the person reading it to sense the BS.
It wouldn't be used to fly plane without lots of physical buttons as a fallback.
Composing rigid instructions for computer is already hard, even with precise semantics defined. Even with static typed, dynamic typed, developers will try hard to get rid of a single bug.
AI will serve as a middleware with an objective of arbitrary result.
Human
|> UI (request)
|> AI
|> UI (response)
|> Human
|> UI (request with heuristic)
|> Computer does thingNot today. Not yet.
RETRO - Improving language models by retrieving from trillions of tokens (2021)
> With a 2 trillion token database, our Retrieval-Enhanced Transformer (Retro) obtains comparable performance to GPT-3 and Jurassic-1 on the Pile, despite using 25× fewer parameters.
https://www.deepmind.com/publications/improving-language-mod...
I had a few of my friends message it. For the non-technical friends, it was amazing to see the transcripts. Even though they knew it was an AI (superhuman response times), they had full conversations with it as if it were a human. Some of them chatted for over an hour!
A lot of people loved using it as a friendly explainer, basically a human interface on top of wikipedia. Other people used it as a sort of therapist, just dumping their problems and thoughts and it would respond in a helpful and friendly way.
Most people had no idea AI had progressed to this point, and I'm sure they could have been convinced that this thing was actually conscious.
Of course, my technical friends very quickly found the edge cases, getting it to contradict itself, etc.
I've had some ideas on how use OpenAI's embeddings API to give it more long-term memory (beyond the 100 most recent messages) which should clear up a lot of coherence issues. Gonna implement that as my next weekend hack.