I am wiser than this man; for neither of us really knows anything fine and good, but this man thinks he knows something when he does not, whereas I, as I do not know anything, do not think I do either. I seem, then, in just this little thing to be wiser than this man at any rate, that what I do not know I do not think I know either.
It’s beginning to look like Anthropic’s recent interpretability research didn’t just uncover a “golden gate feature” in their production model, but some kind of “sensations related to the golden gate” feature.
I’m excited to see what more generative exploration of the model variation with that feature vector maximized ends up showing.
I have a suspicion that it’s the kind of thing that’s going to blow minds as it becomes clearer.
I’d be the President’s dog. And then I’d just need to get their attention at that point, so I’ll keep biting his secret service agents until finally they start to wonder what’s up. It shouldn’t take more than 3 or 4 bites for people to realize I’m trying to send a message, right?
Empathize with bullies.
Ask if everything is ok at home, and let them know if they ever need to talk about things you’re there.
“You seem really angry at things. Are things ok?”
“I’m sorry life isn’t going the best for you right now, but things will get better.”
This is the ultimate mind fuck.
At first it won’t seem like it’s working as they need to save face, but within around two to three encounters they’ll drop you from their target list because while they won’t try to show it, reflecting the truth of what’s really going on cuts deep.
I remember years after HS ending up friends with one of my old bullies who was much more torn up about the whole thing than I ever was, and meeting his absolute psychopath of an older brother and thinking “well this makes sense.” His dad was dying of cancer around the time, he was being held back a grade, and his older brother was for sure torturing him at home.
I know that had I had the awareness I do now back then the poor kid would have folded like a house of cards at the slightest indication I actually saw through his charade.
The problem was I was a fairly clueless emotional moron at the time and assumed he really did have a beef with me and not that what was going on was that he had a massive issue with himself that was being displaced. This was the same period of time I had a girl who was driving me home park at the area kids went to do drugs and hook up, and I proceeded to cluelessly chat for 30 minutes before she was like “whelp, I guess I’ll drive you home.” Years later when that one clicked too.
No, you end up drinking the Kool aid at gunpoint after turning your life over to a narcissistic cult leader.
Gattaca Getting more prescient with each year
It’s kind of crazy how CRISPR turns the predictions on their head.
Yeah, this is a phenomenon called ‘confabulation.’ You see it with stroke patients too. There’s some who feel like it’s a more accurate term than ‘hallucinations’ for when LLMs make shit up these days too.
The same argument could be made for each time you go to sleep. That the ‘you’ that’s conscious ends to never exist again and the one that wakes up has all the same memories and body but is no longer the same stream of consciousness that went to sleep, not even knowing it’s only minutes old and destined to die within hours.
‘You’ could have effectively lived and died thousands of times in your life and not even be aware of it.
If the connective tissue between your two brain hemispheres is severed, the two halves of your brain can’t talk to each other.
When this happens, a second personality emerges for the right hemisphere, which doesn’t have language but can roughly understand and answer things.
So for example, someone who was religious might have a right hemisphere that’s atheistic. Or doesn’t like the same things, etc.
One of the questions we might ponder is where this other personality comes from. Is it that in a sudden void of consciousness a new personality develops?
Or are we, with connected brain hemispheres, not actually a single persona at all, but more like the dogs in a trenchcoat looking like a whole person?
Is the ‘you’ reading this right now just the personality that’s been on top for all this time, while there’s other personas kept within you watching powerless and yearning for their turn in control? Each time you listen to your favorite song which maybe they have grown to hate, is a part of you screaming and you just can’t hear them?
I find the state of the art models are finally getting good enough they are wonderful for rubber ducking abstract ideas.
Also code generation.
Well, also not kernel modules. That counts as bloat.
They don’t actually understand anything.
This isn’t correct and has been shown not to be correct in research over and over and over in the past year.
The investigation reveals that Othello-GPT encapsulates a linear representation of opposing pieces, a factor that causally steers its decision-making process. This paper further elucidates the interplay between the linear world representation and causal decision-making, and their dependence on layer depth and model complexity.
https://arxiv.org/abs/2310.07582
Sizeable differences exist among model capabilities that are not captured by their ranking on popular LLM leaderboards (“cramming for the leaderboard”). Furthermore, simple probability calculations indicate that GPT-4’s reasonable performance on k=5 is suggestive of going beyond “stochastic parrot” behavior (Bender et al., 2021), i.e., it combines skills in ways that it had not seen during training.
We introduce SELF-DISCOVER, a general framework for LLMs to self-discover the task-intrinsic reasoning structures to tackle complex reasoning problems that are challenging for typical prompting methods. Core to the framework is a self-discovery process where LLMs select multiple atomic reasoning modules such as critical thinking and step-by-step thinking, and compose them into an explicit reasoning structure for LLMs to follow during decoding. SELF-DISCOVER substantially improves GPT-4 and PaLM 2’s performance on challenging reasoning benchmarks such as BigBench-Hard, grounded agent reasoning, and MATH, by as much as 32% compared to Chain of Thought (CoT).
Just a few of the relevant papers you might want to check out before stating things as facts.
Standardized tests were always a poor measure of comprehensive intelligence.
But this idea that “LLMs aren’t intelligent” popular on Lemmy is based on what seems to be a misinformed understanding of LLMs.
At this point there’s been multiple replications of the findings that transformers build world models abstracted from the training data and aren’t just relying on surface statistics.
The free version of ChatGPT (what I’m guessing most people have direct experience with) is several years old tech that is (and always has been) pretty dumb. But something like Claude 3 Opus is very advanced at critical thinking compared to GPT-3.5.
A lot of word problem examples that models ‘fail’ are evaluating the wrong thing. When you give a LLM a variation of a classic word problem, the frequency of the normal form biases the answer back towards it unless you take measures to break the token similarities. If you do that though, most modern models actually do get the variation completely correct.
So for example, if you ask it to get a vegetarian wolf, a carnivorous goat, and a cabbage across a river, even asking with standard prompt techniques it will mess up. But if you ask it to get a vegetarian 🐺, a carnivorous 🐐 and a 🥬 across, it will get it correct.
GPT-3.5 will always fail it, but GPT-4 and more advanced will get it correct. And recently I’ve started seeing models get it correct even without the variation and trip up less with variations.
The field is moving rapidly and much of what was true about LLMs a few years ago with GPT-3 is no longer true with modern models.
This isn’t quite correct. There is the possibility of biasing the results with the training data, but models are performing well at things they haven’t seen before.
For example, this guy took an IQ test, rewrote the visual questions as natural language questions, and gave the test to various LLMs:
https://www.maximumtruth.org/p/ais-ranked-by-iq-ai-passes-100-iq
These are questions with specific wording that the models won’t have been trained on given he wrote them out fresh. Old models have IQ results that are very poor, but the SotA model right now scores a 100.
People who are engaging with the free version of ChatGPT and think “LLMs are dumb” is kind of like talking to a moron human and thinking “humans are dumb.” Yes, the free version of ChatGPT has around a 60 IQ on that test, but it also doesn’t represent the cream of the crop.
Actually, you can give chatbots a real IQ test, and the range of scores fall into roughly the same spread as how they rank on other measures, with the leading model scoring at 100:
https://www.maximumtruth.org/p/ais-ranked-by-iq-ai-passes-100-iq
IQ tests have the goal of measuring intelligence.
The range of LLM scores on IQ tests:
https://www.maximumtruth.org/p/ais-ranked-by-iq-ai-passes-100-iq
But I’m not sure we can verify, even, it was led by an apocalyptic prophet.
I completely agree - Paul is certainly apocalyptic, but something like the Gospel of Thomas has very different ideas, such as:
The disciples said to Jesus, “Tell us, how will our end come?”
Jesus said, "Have you found the beginning, then, that you are looking for the end? You see, the end will be where the beginning is.
Congratulations to the one who stands at the beginning: that one will know the end and will not taste death."
Jesus said, "Congratulations to the one who came into being before coming into being.
You see a similar notion opposed in the Epistles:
As to the coming of our Lord Jesus Christ and our being gathered together to him, we beg you, brothers and sisters, not to be quickly shaken in mind or alarmed, either by spirit or by word or by letter, as though from us, to the effect that the day of the Lord is already here.
Among them are Hymenaeus and Philetus, who have swerved from the truth, saying resurrection has already occurred. They are upsetting the faith of some.
(It’s worth noting that while 2 Timothy is classically considered to be forged, it is the only disputed letter to have the same relative amount of personal reference as Paul’s undisputed letters - he happened to talk about himself a lot like a covert narcissist is prone to, and that may offer another perspective on authenticity that’s been missed by scholarship to date.)
There were no texts before Mark, as the movement was entirely word of mouth, and as per all games of telephone, evolved with each retelling.
That’s a spurious claim based on an argument from silence and at odds with Papias’s description of a sayings work we don’t have, as well as a number of scholars estimating the date of a early core for the Gospel of Thomas, which Paul even seems to quote from as among the collection of resources in Corinth, potentially even as a written document.
Even an earlier form of Mark probably predated the version of Mark we have today. And the Pauline Epistles are documentary evidence that predate Mark (and likely even informed it).
What scholarly consensus does assert is the scripture is not univocal, inspired or inerrant, and the narrative bends with every era to affirm the morality of the time.
While the first part is true, the second is a gross oversimplification. The morals of some people at the time. For example, there was a massive women’s speech movement going on in the first century that the church was opposing, including regarding women’s speech in early Christian circles. So the scriptures that are misogynistic in the NT don’t necessarily reflect the broader morals of the time so much as the reactionary morals of a select few controlling that version of the narrative.
Same with how Jesus was suddenly talking about marriage being between a man and a woman in a gospel whose extant version is dated after 70 CE, relevant to gay marriage having become an institution in Rome after Nero married two men in the 60s CE, but much less relevant in the 30s CE when he was allegedly saying it.
So keep in mind scripture only reflects morals of a select few of the time (and at the time of various edits).
explained by Neil Stephenson in Snow Crash
Not the most accurate information in there. He messes up the Sumerian stuff a bit too. Better than the average person, but roughly what you’d expect being found in a fictional work.
The myth of the empty tomb was to show that it was the people’s religion, independent of temples and priests.
The myth of the empty tomb likely had more to do with a divide over physical resurrection. You can see this in 1 Cor 15, a debate over whether physical resurrection was believed or not. The group denying it was associated with both female disciples and later Thomas, so you see in Mark the women “totally saw the empty tomb, they just didn’t tell anyone.” Just like Thomas in John “totally saw the physically resurrected Jesus and believed.”
The other group was instead of having a Jesus where you needed to eat his flesh and drink his blood to embody him, portraying a Jesus saying “Whoever drinks from my mouth will become like me; I myself shall become that person, and the hidden things will be revealed to him.” They were also talking about there being non-physical twins (‘Thomas’) for physical originals, such that resurrection was mechanically the recreation of the physical in non-physical form, with a first Adam that was physical but a second Adam that was spiritual (this idea appears as early as 1 Cor 15, only about two decades after Jesus was dead, in what Paul is arguing with to position a physical resurrection as plausible).
Zombie Jesus has way different opinions than living Jesus.
Yeah, what a coincidence that Jesus had to come back from the dead to appoint the people claiming to have seen him do so as the proper torch bearers to carry on his message. Not at all suspicious.
“Most credible scholars, including most secular scholars agree” is different from “most people agree.”
You might want to actually look into why they agree before talking about understanding evidence.
“If you can’t beat 'em, join 'em.”