Re:Llama2.c L2E LLM – Multi OS Binary and Unikernel Release
by beardedwizard on Saturday August 26, 2023 @07:42AM
(#37271879)
Pretty reasonable, I suggest you mention something along these lines to avoid further misconceptions
Re:Llama2.c L2E LLM – Multi OS Binary and Unikernel Release
by AMICABoard on Saturday August 26, 2023 @07:54AM
(#37271959)
Will be updated with the next commit.
Re:Llama2.c L2E LLM – Multi OS Binary and Unikernel Release
by beardedwizard on Saturday August 26, 2023 @11:51AM
(#37273929)
An aside, any idea why this comment is being downvoted? Seems like a productive exchange.
Re:Llama2.c L2E LLM – Multi OS Binary and Unikernel Release
by AMICABoard on Saturday August 26, 2023 @12:41PM
(#37274397)
Pressing the up arrow beside the comments is upvote right? I hope this doesn't have some inverted logic.
Re:Llama2.c L2E LLM – Multi OS Binary and Unikernel Release
by AMICABoard on Saturday August 26, 2023 @12:39PM
(#37274378)
No idea. I have just upvoted your comment.
Re:Llama2.c L2E LLM – Multi OS Binary and Unikernel Release
by beardedwizard on Saturday August 26, 2023 @12:57PM
(#37274549)
I figured it wasn't you :), anyway cheers buddy!
Re:Llama2.c L2E LLM – Multi OS Binary and Unikernel Release
by AMICABoard on Saturday August 26, 2023 @01:25PM
(#37274852)
I have updated the description and added the requested clarification.
To avoid trolls and invisible downvotes, you can always use github issues. You are welcome there.
Thanks for the initial question. Ultimately it seems that there must always be a human in the loop somewhere.
What I have in mind is -
1. Topic specialized models which are frequently updated maybe every month or two.
2. Fact Checking & Moderation specialized, models which moderate or do fact checking on other model's output.
Kind of a chicken and egg problem. But I believe on the way we will be able to minimize the effects of hallucinations through output validation (both neural and rule based).