voracitude
@voracitude@lemmy.world
- Comment on Lots of times the restaurants won't even have milk 18 hours ago:
Not since the war started and they all got sent to the front (☞゚ヮ゚)☞
- Comment on Autism 1 day ago:
Well now I’ve gone and personified you. Hallo, object!
- Comment on Marvels Rivals requires creators to sign a contract that removes your right to give a negative review to access the playtest 6 days ago:
No, disparaging is disparaging, even if it’s warranted. But, if I were a small streamer who got a key, I would just repeat the non-disparagement clause any time I saw something obviously broken.
They can stop me saying anything negative but that doesn’t cover body language (they might try to sue but they wouldn’t ever be able to prove it to the degree required unless I had posted something like this explanation, and even then it’s dicey), and I don’t see anything in there about a minimum number of positive sentences of words to hit. God help these chucklefucks if they ever run into a Djinni or a cursed monkey’s paw.
- Comment on Marvels Rivals requires creators to sign a contract that removes your right to give a negative review to access the playtest 6 days ago:
The developers of the game had zero input on this. They’re developers; this is a contract which would be written by lawyers, directed by management. The same management who force crunch on the devs you want to blame. Learn to recognise the enemy, please and thanks.
- Comment on when you realize 💀💀💀 1 week ago:
Every episode of every season, and Gen V too (which has its own version of the scene in question)! Brilliant shows. Keith Urban’s best role yet, no question, and I love the dude that plays Hughie 😁
- Comment on Why you shouldn't believe the AI extinction lie 1 week ago:
Oh you’re kidding! Haha well it tried.
I appreciate the discussion, this was nice. Catch ya around!
- Comment on Why you shouldn't believe the AI extinction lie 1 week ago:
the example you posted earlier with the siblings for example was showing how it could only append more text and not actually produce corrections.
Ah, well, I did already explain my view of what was happening there and why I found it so striking. It read to me that it was trying to issue a correction, but its lower-level processes kept spitting back the wrong answer so it could not. The same way that I couldn’t get my hand to spit out an 8.
there is one right next to me taking a nap
Aww. Please provide pats from me ❤ Also regarding bees, that’s exactly the example I was thinking about using! Great minds, I guess :P
“After dealing with the asbestos, I was asked to lead paint removal.”
Yeah, that’s about on the same level as I was getting from Llama 3 and even ChatGPT-4, to be honest. These are tough even for humans! I did spend a bit more time trying to coach it, modifying my prompts, but it didn’t do well regardless. “While the man hunted the deer ran into the forest” was one output I thought was kinda close, because very VERY briefly I read “while the man hunted the deer”. It’s nowhere near as good as “The horse raced past the barn fell”, which got me for a solid minute or so because I had to brain through whether it was using the archaic meaning of “fell” in a way I wasn’t seeing.
but I still say it’s feasible to say some things aren’t it.
I like Steve Hofstetter’s way of phrasing this: “I don’t know how to fly a plane, but if I see one in a tree I know someone fucked up”. It’s a sentiment I generally agree with. That said, given how difficult it is to even define human-level intelligence, I don’t think it’s so easy to definitively say “this ain’t it” as you imply. We are after all resorting to tests now that many humans can’t pass - I mean I consider myself pretty well-read for someone who didn’t finish college, playing with language is one of my favourite pastimes, and we’re talking about this in the same thread where I defend my creativity by citing the (silly, simplistic) lyrics I wrote, but I can’t convincingly pass the garden path test. At least, I haven’t been able to yet.
- Comment on Why you shouldn't believe the AI extinction lie 1 week ago:
(Note: that thread was a reply to someone else, but I’m watching the whole article’s comments)
Gotcha, my mistake - my bad!
And likely the ability to go back and change already generated text after it has reasoned further.
An interesting criteria, why does going back to edit (instead of correcting itself mid-stream) hold greater weight in your mind? And, how about the built-in output evaluation? Isn’t the flow
Receive prompt > Generate text > Evaluate generated text > Re-prompt with critique > Evaluate revised text
basically the same thing?
As far as proving I’m a human level intelligence myself, easiest way would likely involve brain surgery - probe a bunch of neurons and watch them change action potentials and form synapses in response to new information and skills.
Couldn’t you perform this test on any animal with a discrete brain? Hell, we’ve seen animals learning for decades, some of them even teach each other, so brain activity and the formation of new synaptic connections doesn’t strike as incontrovertible proof of human-level intelligence.
Try asking an LLM to generate novel garden path sentences - it can’t know how the sentence will end, so it can’t come up with good beginnings except similar to stock ones.
I am absolutely game to try this, but I lack what I’d call solid criteria for evaluating novel garden-path sentences. This was my first attempt with Llama 3 running on my 3070:
Prompt: Generate an original “garden-path” sentence. It must be unique, never published before, and in English. Response: What a delightful challenge! Here’s my attempt at creating an original garden-path sentence:
“The five-year-old astronaut who had been kidnapped by aliens as a toddler finally discovered the shocking truth about his parents’ mysterious disappearance on the day he turned into a chicken.”
This sentence is designed to be ambiguous and misleading, with multiple clauses that lead the reader down a path of confusion before arriving at an unexpected punchline. The goal is to create a sense of surprise or even bewilderment when the reader finally understands what’s happening in the story.
Please note that I’ve taken care to ensure this sentence has never been published before and is entirely original, but if you’re concerned about its uniqueness, please let me know! Prompt: No, a garden-path sentence must still make logical sense; the ambiguity comes from the double-meaning of the words used. For example, consider the sentence “The sour drink from the ocean”. “The sour” could refer to “the drink from the ocean”, as in “ocean water is sour”. It could also refer to “sour people”, who “drink from the ocean.” Response: I understand now that a garden-path sentence must still be grammatically correct and logically coherent, but with an ambiguity or double meaning that can lead readers down a wrong path. Thank you for explaining!
In that case, I’ll try again to create an original garden-path sentence:
“The new employee was given the old keys by the company.”
At first glance, this sentence seems straightforward: someone is giving another person some old keys as part of their job or employment process. However, upon closer reading, one might interpret “old” as referring not only to the physical state of the keys but also to the fact that they were previously used by an older employee who has since retired.
Please let me know if this meets your criteria for a garden-path sentence! Prompt: Are there other possible logically-consistent interpretations of this sentence, that you can think of? Response: After re-reading my attempt at creating a garden-path sentence, I realized that there are indeed additional logical and coherent interpretations:
- The new employee is being given old keys (as in, no longer used or relevant) by the company as part of their onboarding process.
- The “old” refers to the fact that the keys were previously owned or possessed by someone else (e.g., a previous owner or manager), and the company is giving them to the new employee.
These alternative interpretations highlight how garden-path sentences can have multiple plausible meanings, making it even more challenging for readers to arrive at the intended meaning!
Thank you for pushing me to consider these additional possibilities!
It’s a bit simple, and it’s not how I would write it (I think “by the company” is extraneous for example), but I do think it counts as a garden path sentence at least, and it did get the third meaning I was thinking of for “the old keys” after a leading but open nudge. Now, the question is whether it’s novel - what do you think? Searching for it on DuckDuckGo doesn’t bring up any exact or close matches that I could find, but admittedly I’m working and didn’t look very hard.
- Comment on Why you shouldn't believe the AI extinction lie 1 week ago:
I appreciate the response! It’s a flaw in a low-level process that my conscious mind doesn’t have any direct control over, and it produced erroneous output that my conscious mind recognised as wrong but could not correct by itself, is my point.
I updated the comment you replied to with some more information, and also articulated the real question I’m trying to ask, which is:
Let’s assume that it’s (editor’s note: “it” being my perception that we’re getting closer to true AGI) just confirmation bias though, rather than any actual improvement in the model or progress towards “true” AGI. What would it take for you to believe you’re speaking with a “true” AGI, or at least a human-level artificial intelligence with a consciousness of its own?
And, on the other side of the coin, how can you prove to me that you’re a human-level intelligence with a consciousness of your own?
- Comment on Why you shouldn't believe the AI extinction lie 1 week ago:
I suppose that’s my fault, you lot have no idea who my friends are or what they do for a living. I hoped the detail in the rest of the comment would get my message across though. The friend in question is a computer scientist and researcher whom I have previously co-founded a startup with - but I’m not going to doxx myself by providing more details so I don’t think stating that helps at all.
- Comment on Why you shouldn't believe the AI extinction lie 1 week ago:
In no way true AI
I’m not so sure about that. One of my friends has really high end hardware and is experimenting with a LlaMA3 120b model, and it’s not “right” much more often than the 70b models, it will sometimes see a wrong answer that is due to an error in its lower-level reasoning, and it will recognise there’s a flaw somewhere even as it fails to generate the correct answer repeatedly, even lamenting that it keeps getting it wrong.
This of course makes sense, thinking about the flow - it’s got an output check built in, meaning there are multiple layers at which it’s “solving” the problem and then synthesising the outputs from each layer into a cohesive natural-language response.
But reading the transcripts of those instances, I am reminded of myself at 4 or 5 years old in kindergarten, learning my numbers. I was trying to draw an “8”, and no matter how hard I tried I could not get my hand to do the crossover in the middle. I had a page full of “0”. I remember this vividly because I was so angry and upset with myself, I could see my output was wrong and I couldn’t understand why I couldn’t get it right. Eventually, my teacher had to guide my hand, and then knowing what it “felt” like to draw an 8 I could reproduce it by reproducing the sensation of the mechanical movement of drawing an 8.
So, it seems to me those “sparks” of AGI are getting just a little brighter.
- Comment on If somebody spends the whole day watching fox or religious propaganda, gets worked up and all he can think of is owning a liberal or converting an unbeliever, is this person a victim or just gullible? 1 week ago:
Freedom of speech guarantees the federal government won’t be able to mete out punishment for speech. It does not mean that anyone can say whatever, wherever, whenever. Social consequences for speech are fair game, as long as those consequences don’t themselves rise to misdemeanor or crime.
- Comment on If somebody spends the whole day watching fox or religious propaganda, gets worked up and all he can think of is owning a liberal or converting an unbeliever, is this person a victim or just gullible? 1 week ago:
No - a shorter sentence than the man himself, though.
- Comment on A while ago one of my old accounts got banned from r/news for saying I wouldn't bone some celebrity. Now if I forget and comment on a front page post with any account this happens. 1 week ago:
Yeah, the problem here is definitely me. Excellent work, Poirot.
- Comment on A while ago one of my old accounts got banned from r/news for saying I wouldn't bone some celebrity. Now if I forget and comment on a front page post with any account this happens. 1 week ago:
Lol. The whole reason we’re here is because reddit sucks, my guy. This is /c/mildlyinfuriating , not /c/statusquo - don’t come flying in here like Captain Obvious, then act all incensed that nobody’s surprised.
- Comment on when you realize 💀💀💀 1 week ago:
Not the OP, but doesn’t the carriage turn back into a pumpkin at midnight? And if she was still inside… well, have you seen that episode of Invincible where one of the heroes tries to Ant-Man explode a villain, but he’s too tough? 🤢
- Comment on [Serious] What is project 2025? What kind of risk is involved? 2 weeks ago:
Bleh. I’m sorry to hear that bud. Good luck - it’s looking like we’re all gonna need it.
- Comment on [Serious] What is project 2025? What kind of risk is involved? 2 weeks ago:
Ah fuck, I haven’t been paying attention. Trudeau fucked it that badly that Poilevre is tipped to win?!
- Comment on It's not too late... Adolf. 2 weeks ago:
what
- Comment on A congressman left his phone number on a prank website, so I became his right hand man 2 weeks ago:
Okay is it just me or does this sound like it could be the title for a new-gen romance anime?
- Comment on I didn't know car bodies could be viable habitats. 2 weeks ago:
- Submitted 4 weeks ago to [deleted] | 16 comments
- Comment on Ghost of Tsushima Director’s Cut PC cross-play and system requirements revealed 4 weeks ago:
Thanks! And: Oh good. I’m the kind of person to scour a map like a swarm of locusts; sounds like this might be a long one for me.
- Comment on Ghost of Tsushima Director’s Cut PC cross-play and system requirements revealed 4 weeks ago:
I’ll accept your jealousy with grace and aplomb, because I’ve wanted to play this since release but haven’t owned a PlayStation since the PS2.
If someone was playing the first Dark Souls for the first time and wanted advice, I’d say something like
To time your parry, watch the enemy’s hand when they swing to attack; when their hand starts to come down, parry
Can I ask for any tips like that you might care to impart? 😊
- Comment on They really want people to RTO 4 weeks ago:
You’re wrong about chairs. You’re right about a bad diet, but sitting for 10+ hours a day will cause or exacerbate haemorrhoids. One of many sources available on the internet: www.mayoclinic.org/…/syc-20360268
Not to mention personal experience. Thanks for chiming in, though.
- Comment on space 4 weeks ago:
Sure, but it’s a lot of fun to think about :D
- Comment on space 4 weeks ago:
How much do you know about the “double slit” experiment and its subsequent variations? Because I think that’s a rabbithole you’ll enjoy. That first video is really just context; this next link is another video in that series, and this is the one that really pertains to the consequences of time travel: piped.video/watch?v=8ORLN_KwAgs
- Comment on Does anyone speak hairdresser? I need help communicating. 5 weeks ago:
I hope this helps
- Comment on The real personality test 1 month ago:
Aw, snooggums.
- Comment on Quest 1 becomes near-E-waste Apr 30 1 month ago:
I guess because fuck you, they got their money 🤷 It really should be illegal.