Socrates comes from a period, the tail end of that period, where all learning was oral. Writing was "new". He observed, which is provable and true, that learning from a written word perspective is a weaker form of learning than from an oral perspective. From the simple fact that when information is delivered orally, questions can be asked, it is a 2-way communication. Not so with writing. With writing, the student must follow their reading with additional oral use and trial uses of the information, or it is lost completely. While that same information initially gained in understanding via oral lessons can often be put to use immediately, the oral instructional path is more complete, it allows questions and answers during the learning process. While a written lesson requires human interactions to supplement that learning for it to hold.
>that learning from a written word perspective is a weaker form of learning than from an oral perspective
Yea, this isn't one that is proven from empirical data. The oral instruction path not more complete by any way possible. The combination of reading + writing at the same time is super powered in comparison. It stops the human brain from becoming a hallucination machine about the actions it took in the past, and allows more truthful retrospection.
The origin of rhetoric is oral persuasion, not the transfer of objective information. Oral conversations are noisy AF, easy to dominate, allow speakers to lie with "I didn't say that", and to use persuasive rhetorical tricks to confuse and persuade instead of enlightening.
We've all been in meetings where people talk at each other, or everyone says their part with no connection to the rest, and previous points are forgotten almost immediately even if they're valid, true, relevant, and important.
Likewise lectures - good luck teaching anything scientific without allowing notes.
Writing gives the recipient time to stop, ponder, understand, and - on a good day - disagree and criticise.
It doesn't prevent questions at all. It encourages them, and gives them time to mature and deepen. You may not be able to ask the original writer - especially if they're dead - but you will always be able to find comments and opinions from others.
If you put all of these together you get an argument from status, not from effectiveness.
Being a teacher/philosopher was a career, and writing endangered that.
Superficial in-the-moment wit and memory were always better for entertainment than expanding human knowledge.
Well, spoken exchanges are not expected to be neutral. That's part of the nuance of communications. Yes, oral conversations are noisy, easy to dominate and speakers can lie, which is also part of the lessons within understanding how to communicate well. Lessons that somehow magically also teaches a person to plan their communications, to employ both critical analysis and secondary considerations in reflection of their audience. And to do that in real time while conversing.
Comparing the lax and informal communications of our modern experiences, it is no wonder that people cannot imagine the environment a community a quality communications creates.
Our collective communications experiences are argument from status, not from effectiveness, but that is not to say effective communications and the completely other environment it creates does not exist. Socrates speaks of that environment, not our modern failure to communicate above 5-grade levels.
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.
reply