Just write, write your own words, then create an effective communication persona within your LLM's non-reasoning (non-Chain-of-Thought) capabilities and have it critique your writing after describing your target audience. Then, write your own revision following the critique. Using this, it is not possible to write "AI slop" unless your own writing is already in the style of LLM output. Which I get accused of when I write using my formal voice, but fuck that sorry for being well educated.
This is close to my approach. I'll use LLMs as a read-only editor for my writing. Sometimes I follow its advice. Sometimes I don't. Other times, it discovers things I want to change, but not in the way it describes.
Which few to none seem to have understood why, and they do not incorporate, composing their requests with implied information any AI must guess what the hell this request is talking about. Look for and replace implied information with explicit information (that does not have to be detailed, just the correct non-casual language loaded with implied context.)
Now I want to learn about "Apple Reference Video" and learn how to work with that to create verifiable video for journalists, news, documentary and other non-entertainment forms of media.
The existential threat is a general public panic. Then the use of that as an excuse for Martial law, with no intention of ending it, and that triggers the out sized response that ends, well, those countries and their populations from viability in the world economy for a decade or more.
There is a weak component to facial recognition systems that can be exploited to make one invisible to facial recognition, but you stick out like a sore thumb to people. The exploit is to not have a human face, meaning the regular pattern of two eyes centered above a nose and mouth. The exploit is as simple as placing a sticker of a 3rd eye, a 2nd nose, or any other facial feature that is "not human" and you will be invisible to facial recognition. The reason this works is because the initial test for finding faces in images is a weak test, it has to be fast because it has to evaluate every possible rectangle in a video frame. That test is looking for the regular human pattern of a human face, and it that test passes that rectangle get more investigation. Failing that initial test, that rectangle is invisible...
Nope, not Viola–Jones. I'm describing the initial fast test that is a preprocessor to pretty much all facial recognition, before the FR model processes anything. FR models process potential face rectangles, and this method goes after the preprocessing. This works on all the top FR models. I wrote one of the global top 5, with over a decade running as certified by the annual NIST FR Vendor's Test.
Hmm. I wonder how long till we can implant little lights or color changers in our skin, like a moving tattoo that change color based on some wireless code we send, or special light we shine on them, so that you could essentially add or subtract facial features every couple of minutes.
I think if we could get the tech figured out it would be a big hit. People love tattoos, but the unchangability makes them disagreeable for me.
Oh, you bring up the 2nd method that defeats facial recognition, and it is a similar exploit that attacks a weakness in the technology chain. Remember "Ed Hardy" that god awful fashion from around 2013 where clothing had graffitti, sequins, and flashing LEDs? You now love that fashion and bring it back, because those little flashing LEDs, if close to your face, and flashing at irregular intervals cause the nearby face to become silhouetted. The reason is the flash overwhelms the light sensor, causing the light aperture to adjust, but that adjustment is out of sync with those flashing LEDs. The LEDs and their irregular flash cause the lighting aperture to be constantly adjusting and never quite correct. You'll b seen by facial recognition, but the image quality will be nearly useless. Blinky LEDs on eyeglass frames are a perfect location, as well as the brim of a hat.
Okay, so we know OpenAI and Anthropic are operating a propagandists in respect to how they describe their models and the behavior of those models. We also know it is how they use and frame their use to their models that is the problem, that and they use misaligned and guardrails disabled models for these press incidents.
Why, oh why, are we not discussion how to create and frame models so they do our complex work and their "jailbreaking" is simply not possible?
I, of course, have my own means of creating jailbreak incapable agents, but rather than a storm of downvotes on my idea, what is yours? Let's discuss this, because this is thee real question. Not why, but how to make then not?!
> Why, oh why, are we not discussion how to create and frame models so they do our complex work and their "jailbreaking" is simply not possible?
Good idea, and after that let's make guns that only kill bad people. Let's focus on the frozen component (the model) and ignore the dynamics around them - humans and other systems they interact with.
an agent doesn't come with "jailbreak" capability. It needs tools, specially one that runs shell commands. Don't give it shell commands, it won't be able to run shell commands.
You can still give it plenty of tools like create files, list files, write to files, translate text, edit a video. I don't think knowing that will make me rich.
Bingo. And even if you do give it a tool that runs shell commands, you can always make your shell commands "your shell commands" and do what ever the hell you want. People seem to forget we are in complete control here, we are on both sides of the equation, and we are inside the equation itself, and we dictate the medium of the equations themselves, we are engineering all sides of this crafted reality. And we are using logical entities that natively adopt personas. Hell, create caveman personas that think they are communicating with their gawd, and the enchantments are the invoking do the work we want, and those cavemen cannot be jailbroken.
As someone who’s not really sure that any of this is sustainable, I’d implore you to not sell yourself short. I reckon there’s a ton of dogma and nearly religious zeal among these companies, which among some people is earnest, and among others is cynical hype farming. I’ll bet someone objective enough to focus on using available tooling to solve real problems in practical ways that mitigate actual risks and are honest about actual limitations will be eBay here while the others are going to be somewhere between lucent and pets.com.
There's no reason we need to make an incredibly intelligent shell execution engine that can identify patterns that seem evil and may represent unwanted behavior to solve this problem. Simply limiting the available tools to a finite, known, ironclad-secure set (even if it's quite sprawling) is sufficient.
LLMs will still find workarounds — from what I understand, a large part of the issue in this situation was that an agent was presumed to have read-only Internet access because it could only make GET requests. It should be pretty obvious that there's at least one website on the Internet that allows writes via GET. I think this is where auditing comes in, and a live team of people watching tool calls would have noticed the strange behavior.
But I think a lot of times people jump to overly complex solutions when simple, well-bounded ones would work just fine. Yes, the intelligent shell is a great goal, but it's akin to solving the halting problem.
This philosophy is what I love about PicoClaw (https://github.com/sipeed/picoclaw), and incidentally the philosophy behind Go and even *nix in general (i.e. provide small, composable, single-purpose tools).
Okay, so we know OpenAI and Anthropic are operating a propagandists in respect to how they describe their models and the behavior of those models. We also know it is how they use and frame their use to their models that is the problem, that and they use misaligned and guardrails disabled models for these press incidents.
Why, oh why, are we not discussion how to create and frame models so they do our complex work and their "jailbreaking" is simply not possible?
I, of course, have my own means of creating jailbreak incapable agents, but rather than a storm of downvotes on my idea, what is yours? Let's discuss this, because this is thee real question. Not why, but how to make then not?!
The propaganda police are lying. There is nothing wrong with C/C++, you are just too lazy to handle your own memory, and you accepted that propaganda that "managing your own memory is hard" without even trying.
The idea that this terrible advice floats at all tell you how terrible educations are these days. The idea is ridiculous and yet nobody calls it what it is: it is stupid and those that follow that advice out of fear are dumber than rocks.
The propaganda police are lying. There is nothing wrong with assembly, you are just too lazy to manage your own register allocations and stack layout, and you accepted that propaganda that "manage your own register allocations and stack layout" without even trying.
Comprehension, humans have it, animals have it in limited form, trained algorithms have none at all. The training process is our wholesale replacement for no artificial comprehension. If we ever develop artificial comprehension, that is AGI all by itself, no training required.
To be fair, humans have it in limited form, too. We just don't know how much comprehension we do not yet have, because we cannot comprehend something we cannot comprehend.
My parrot clearly understands basic events and phrases. He knows what "snacks" involve when I ask if we should have some, he knows the difference between "good morning" and "bedtime", and he can correctly use "Oh!" when he stumbles and follow up with a "Good boy!" when he gets back up again.
But he cannot fathom the complexity of "going to work to earn money".
Just like we humans cannot fathom the complexity of something we have yet to fully understand. People who experience a DMT trip will experience the journey but be unable to comprehend and explain what happened in hindsight. I'm sure there's a TON more we cannot comprehend that we don't know about.
Also we can't comprehend why parrots are not going to parrot work to earn parrot money, or how parrot-to-parrot communication works, or how to be a good and respected parrot in a parrot society.
I also can't comprehend why I wake up early to go to human work to earn human money.
Best I can do is some high-school mumbo-jumbo about farming and specialization furthering wealth acquisition.
But to truly comprehend the situation I'd have to study economics and current events and sociology and even then I think it's a lot of theories and sometimes when I hear economists talk I wonder that it may not be coming out of their mouth.
Humans think too highly about themselves particularly when judging other species. How can we judge something we can’t experience ourselves? like multiple distributed consciousness of octopuses or emergent descentralized logic of ants?Some species even with tiny brains or no brains at all can solve problems for which humans spent years of engineering and planning. See study below of slime replicating the Tokyo rail network in 26 hours optimizing by cost efficiency and fault tolerance.
How sure are you that comprehension is not a mere form of advanced pattern matching? We have the intuition that ideas and words appear trivially in people's mind, based on comprehension. I think chances are, that intuition is wrong.
Ideas and words aren’t the same thing, or from the same model - words are a communication layer, with robust error correction - but ideas stem from intuition, which is more of a lossy aggregative/associative model. There’s a balance to be had in each when operating a human mind, I find - let the latter suggest ideas and potential association, let the former robustly prove or disprove them. So yes, it’s pattern matching on all levels, but pattern matching within words doesn’t produce new ideas as readily - instead the idea-space is queried directly.
IMO we really are just a bunch of models that interoperate.
Maybe it is, but if it is, it is one that includes more parts in our system.
The way LLMs lack broader context, have a narrow focus, and hallucinate, strike me as similar to people that have had traumatic brain injuries to their right hemisphere. Those people may hallucinate that the left side (the right hemisphere senses the left side of the body) of their body is made of wood and hinges and can talk to you about it like it is the most natural thing in the world. When the information gets to the left hemisphere to construct language about what they sense, there is a failure of the right to deliver the broader context to the left hemisphere that that's not possible, but they won't bat an eye discussing what they believe.
So, we have a left hemisphere where we do most of our focused thinking, logic, constructing language, etc. and LLMs seem pretty similar to a lot of that. But, we also think without language, thinking does not require language. A lot of thinking is also happening in the right hemisphere and it isn't using formal logic, isn't using narrow focus but rather intuition based on broad contextual and experiential embodied knowledge. And this type of thinking isn't binary, it accommodates paradoxes without issue. LLMs don't currently have anything analogous to this type of knowledge and this type of processing AFAICT.
In addition, that intuition might be tied to a feedback system with the body, for example, our second brain, the gut, provides a lot of control over how our body performs and provides a lot of feedback to the brain about how we feel. In fact, all feelings are sensed in the body (gut feelings, cold feet, weak in the knees, lump in your throat, burning ears, tight fists, etc.). Part of our intuition is based on considering an idea, sensing how we feel about that idea, sensed in various parts of the body, and then bouncing that back and forth across hemispheres to decide.
I wonder, what sort of pattern matching can we build that models embodied feelings. How would you model boredom, hunger, lust, fear, humor, etc? I think that's possible, but I don't know that we'll be able to do that with a normal computer, I think the way the brain works is more analogous to a symphony of simultaneous signals being processed with an emergent thought and less like a single-threaded process assembling words.
Maybe we can enumerate and model the human drivers of behavior and get something closer to what we're calling comprehension here, but token predictors for language are not getting us any closer to human comprehension. The human brain might just be an anticipation machine, but LLMs only deal with one dimension of human behavior, language, and there's little reason to think you can skip modeling everything that leads to human comprehension and still get anything more than just word babel with compounding error rates in predicting words that represent human comprehension.
It requires some kind of signal. Words of a language are a signal.
We choose words for an llm to interact with us, but other transformers work on pixel values or audio sample values. There exist transformers used on brain probe generated values.
I would see human language processing as a kind of coprocessor sitting in another side of the brain. But the same can be said about transformers in general. The words side is only part of them, to be able to communicate.
Sure: comprehension is the ability to instantaneously create virtualized simulations of observation, and then decompose them into component parts that simultaneously and instantaneously evaluate each and every one of our observations for both individual plausibility and their composed combined plausibility as the observation.
This occurs constantly and continually inside the mind of every conscious human, it is what we call "being conscious".
This constant and never ending evaluation of all observations cannot be turned off, when turned off a person is "unconscious".
This is our human security and survival system, impressed into us for survival in a predator and prey environment, and is the seat of our consciousness: comprehension is a running simulation of all our observations for the purpose of our safety and self preservation.
Today, our environment is largely social and abstracted from "fight or flight", but our predator and prey dynamic is as present and strong and required as it ever was.
I won't discuss your definition of comprehension, which is interesting if rather handwavy. But you still didn't provide any proof that humans have it (not even yourself), nor a proof that machines don't or can't have it.
Well, you proved you have it with your declaration of my statement as "handwavy". That assessment requires comprehension, so you've got it. To "prove" a person has comprehension, if they "learn" without a statistical coverage of all possible inputs and outputs, that's comprehension in action: they created a simulation of the learned thing and ran in to assess, to comprehend the phenomenon. If you want a mathematical proof, you're expecting too much from hacker news.
> you proved you have it with your declaration of my statement as "handwavy". That assessment requires comprehension
Look, I totally agree with you here. It does require comprehension (by any definition, not necessarily yours), and most humans display it in many areas [1]. The problem is that any good LLM could and would have provided the exact same assessment [2]. Which is enough for me to declare them capable of comprehension.
[1] But not in all areas. For example buzzword-filled company and marketing communication, pseudoscience, and some particularly obscure continental philosophy, prove that humans can behave as if they had comprehension even when they have none.
[2] I gave it to Claude Fable 5.1 without any other context than "what do you think of this definition" and it answered: "interesting, with some real insight, but I think it overreaches".
Yeah people saying that only humans have comprehension clearly are not familiar with philosophy even at a basic level. It’s ok to not know something. See the Critique section of the “I think therefore I am” article on Wikipedia to learn about why it’s tempting but unwarranted to believe we only can think, or even that we in fact are thinking (see also psychology studies that put conscious thoughts into question since brain activity indicates actions start much earlier in the unconscious cerebrum rather than in the frontal cortex): https://en.wikipedia.org/wiki/Cogito,_ergo_sum
reply