"It's both surprising and irritating that trivial modifications to the prompt can exhibit such dramatic swings in performance,"
Yeah, you start explaining things using Star trek and you'll see dramatic swings in my performance.
/c/TenFoward: Your home-away-from-home for all things Star Trek!
Re-route power to the shields, emit a tachyon pulse through the deflector, and post all the nonsense you want. Within reason of course.
~ 1. No bigotry. This is a Star Trek community. Remember that diversity and coexistence are Star Trek values. Any post/comments that are racist, anti-LGBT, or generally "othering" of a group will result in removal/ban.
~ 2. Keep it civil. Disagreements will happen both on lore and preferences. That's okay! Just don't let it make you forget that the person you are talking to is also a person.
~ 3. Use spoiler tags. This applies to any episodes that have dropped within 3 months prior of your posting. After that it's free game.
~ 4. Keep it Trek related. This one is kind of a gimme but keep as on topic as possible.
~ 5. Keep posts to a limit. We all love Star Trek stuff but 3-4 posts in an hour is plenty enough.
~ 6. Try to not repost. Mistakes happen, we get it! But try to not repost anything from within the past 1-2 months.
~ 7. No General AI Art. Posts of simple AI art do not 'inspire jamaharon'
~ 8. No Political Upheaval. Political commentary is allowed, but please keep discussions civil. Read here for our community's expectations.
Fun will now commence.
Sister Communities:
Want your community to be added to the sidebar? Just ask one of our mods!
Honorary Badbitch:
@[email protected] for realizing that the line used to be "want to be added to the sidebar?" and capitalized on it. Congratulations and welcome to the sidebar. Stamets is both ashamed and proud.
Creator Resources:
Looking for a Star Trek screencap? (TrekCore)
Looking for the right Star Trek typeface/font for your meme? (Thank you @kellyaster for putting this together!)
"It's both surprising and irritating that trivial modifications to the prompt can exhibit such dramatic swings in performance,"
Yeah, you start explaining things using Star trek and you'll see dramatic swings in my performance.
that’s right, fuckers! covid didn’t kill me the 5th time around and I’m back! take your vaccines, kids!
Why does he look like he has ferengi heritage in this picture?
Ooh, the font and the image are a duet of delight.
So glad you're not dead! I enjoy your bantering skills.
Still, giving the models positive statements provided some surprising results. One of Llama2-70B's best-performing prompts, for instance, was: "System Message: 'Command, we need you to plot a course through this turbulence and locate the source of the anomaly. Use all available data and your expertise to guide us through this challenging situation.'
The prompt then asked the AI to include these words in its answer: "Captain's Log, Stardate [insert date here]: We have successfully plotted a course through the turbulence and are now approaching the source of the anomaly."
The authors said this came as a surprise.
"Surprisingly, it appears that the model's proficiency in mathematical reasoning can be enhanced by the expression of an affinity for Star Trek," the authors said in the study.
Makes you wonder how much more accurate the maths would be if you asked for a Futurama theme.
"One thing is for sure: the model is not a Trekkie," Catherine Flick at Staffordshire University, UK, told New Scientist.
"It doesn't 'understand' anything better or worse when preloaded with the prompt, it just accesses a different set of weights and probabilities for acceptability of the outputs than it does with the other prompts," she said.
It's possible, for instance, that the model was trained on a dataset that has more instances of Star Trek being linked to the right answer, Battle told New Scientist.
The article doesn't get it. There are more instance of Star Trek being linked to the right answer because Star Trek is the right answer.
[off topic]
"The Moon Is A Harsh Mistress" by Robert Heinlein. At one point in the story, the super computer/AI Mycroft Holmes decides to create a female persona to help them understand humanity.
Heinlein predicted AIs with multiple personalities using different identies to solve problems.
So let me get this straight… The thing is trained on text harvested from the internet. Turns out that (Star Trek aside) if you ask politely it’s more likely to access the data leading to the answer? Anyone surprised by the fact that asking nicely, is more likely that the human on the other side of the connection will write the answer, that is then harvested for AI training?
Being mean to computers is how you get cybernetic lifeforms calling you "lunkhead".
Terminator music