

I enjoyed his later work in the Portal series
I enjoyed his later work in the Portal series
Aren’t you all enjoying the government efficiency?!
Hooray more oil to chug into the atmosphere to make an unbelievably wealthy person more wealthy
But… Isn’t the actual Jagermeister liquid inside the bottle actually red…?
I wonder if the contents of the files can be called as evidence for the defense.
They probably can’t completely patched in their training, but using a pipeline which reviews the prompt and response for specific malicious attack vectors has proved very successful if adding some latency and processing expense.
You can, however, only run these when you detect a potentially malicious known exploit. If the prompt contains any semantic similarity to grandma telling a story or how would my grandma have done x, for example, you can add the extra pipeline step to mitigate against the attack.
Jfc this guy looks like a live action Earthworm Jim
WHY DID YOU BLENDER EXPLODE
All humans are single tract passing through a fleshy exterior wall. We are just big doughnuts.
Gotta nuke somethin’
Oh thank goodness I’ve been dying for a shit for like 20 minutes
Fuck it and find out
Fuck me have they not patched the grandma exploit yet? I have a book from last year which references that one
I bet you’re wondering how I got here. Funny story actually. It all started…
There are two types of people in this world: those who can extrapolate from incomplete data
Sorry. It’s great that you find peace and love in your faith and I have love for everyone who does.
My comment was in response to the terrible atheist guy in the image wanting to stay home on Sunday and the church promoting Sunday as a day of rest in reflection of God resting on the seventh day of creation. Getting you and your family dressed up, acting normal (at least for me) and then making a meal is not what I would describe as a restful day.
Bias of training data is a known problem and difficult to engineer out of a model. You also can’t give the model context access to other people’s interactions for comparison and moderation of output since it could be persuaded to output the context to a user.
Basically the models are inherently biased in the same manner as the content they read in order to build their data, based on probability of next token appearance when formulating a completion.
“My daughter wants to grow up to be” and “My son wants to grow up to be” will likewise output sexist completions because the source data shows those as more probable outcomes.