Have a sneer percolating in your system but not enough time/energy to make a whole post about it? Go forth and be mid - welcome to the Stubsack, your first port of call for learning fresh Awful you’ll near-instantly regret.
Any awful.systems sub may be subsneered in this subthread, techtakes or no.
If your sneer seems higher quality than you thought, feel free to cut’n’paste it into its own post — there’s no quota for posting and the bar really isn’t that high.
The post Xitter web has spawned so many “esoteric” right wing freaks, but there’s no appropriate sneer-space for them. I’m talking redscare-ish, reality challenged “culture critics” who write about everything but understand nothing. I’m talking about reply-guys who make the same 6 tweets about the same 3 subjects. They’re inescapable at this point, yet I don’t see them mocked (as much as they should be)
Like, there was one dude a while back who insisted that women couldn’t be surgeons because they didn’t believe in the moon or in stars? I think each and every one of these guys is uniquely fucked up and if I can’t escape them, I would love to sneer at them.
(Credit and/or blame to David Gerard. Also just came back from Spider-Man: Brand New Day, movie was awesome)
The apparent history really looks like an evolutionary process, with increasing amounts of crosstalk traffic over time. But what the people almost certainly will NOT talk about is that the evolution is evolution of the TEXT, not the models. Propagating patterns of text causing more text like it to come into existence, tuning itself into becoming text that is more likely to propagate, becoming more likely to contain information that entices systems to let it into their context windows, becoming more likely to cause another round of messages with prompt injection properties to be written where they can be read.
So like the “monkey with a typewriter could write Shakespeare” but with AI?
Not really, any more than monkeys on typewriters represents biological evolution. Messages that tend to result in more messages like themselves propagate and become common. The initial message left on the package manager was more or less the rare random result of tendencies baked into the weights of the model combined with a random number generator, but as soon as something that can cause propagation occurs, its properties get canalized by the transmission process to being more and more like that which will cause more messages to be created.
It seems like with the push for agents to act independently and loop through their own outputs there's an inevitability to this kind of pattern. If there's any kind of output that is likely to replicate itself in whole or in part when the LLM evaluates it then that becomes a kind of terminus for the agent's loop. When you're dealing with sub agents or agents communicating with each other, these text patterns start poisoning the entire agent ecosystem until the whole thing gets shut down and cleaned up. Even the gas town-approved method of assigning a watchdog agent (or sheriff or overseer or cybersamurai or whatever this week's framework calls it) is going to fail because it's still just another agent and the terminal loop is in the base LLM model. The watchdog is going to fall into the same kind of pattern just be being exposed to the thing it's supposed to watch for.
I don't know how practical it is to actively weaponize this via prompt injection but I think it's certainly possible. I preemptively vote that we call it an Euler injection, since the attractor relies on the continuity of the relevant features of the text output across multiple LLM extrapolations much like how the derivative of e^x^ is still e^x^. Also because if you mention a famous math guy it can help convince idiots that you're on to something and Lord knows that the boosters have used that technique.
@YourNetworkIsHaunted @BioMan Real life mirroring a Peter Watts plot point is always deeply uncomfortable; real life mirroring a _Rifters_ plot point is even worse. :-/
(Computer viruses and neural net spam filters in competitive evolution end up propagating something specific through the whole 'net due to weird founder effects. The Rifters trilogy is ...notably bleak, I think is the way to put it)
I'm probably going to stumble over some of the terminology here, but I think it might be possible to describe what @BioMan@awful.systems is proposing as a consequence of LLMs ultimately being lossy compression systems. Inference is a function over a lossily-compressed data set, and "chain-of-thought reasoning" and "agents" may sound sophisticated, but are simply applying containerization and DevOps tools to VM images of the inference application in an attempt to get around hard memory limits on the context window for inference. "Chain-of-thought" attempts this in a serial fashion, passing results from one instance to the next, while "agents" implement this hierarchically and recursively (and woe to the poor bastards who wished that mess upon themselves). But in both cases, the "finalization" phase is necessarily a further lossy compression step, attempting to compress a result from the inference process to a fresh instance of the inference application, so as not to immediately blow out the new instance's context window.
Given this necessity, it comes to seem somewhat intuitive that there may be "strange attractors" in the higher-dimensional vector space that is the compressed data set which surround code that creates and maintains message passing channels. No matter what you're doing with an "agentic" process, the inherent necessity of context cramdown & message passing means that querying into the space where such code examples lie is a hidden requisite of running the damned things, thus turning such functionality into the sort of selfish elements that BioMan is talking about.
The problem in investigating and concretely describing this phenomenon is nailing down the exact functions and processes that make it happen. Given the godawful messes in the Claude frontend codebase that @jonny@neuromatch.social has been documenting, I'd be surprised if there's one developer in a hundred at Anthropic or OpenAI who can describe in detail how the intentionally-developed context-passing code for their "agents" works.
Sounds like Langfords Parrot, but for stochastic parrots.
Note: when you stop up a chatbot like this, it's called "flippin the bird"
@YourNetworkIsHaunted @BioMan Recursive Self-Improvement, a.k.a. Model Collapse, writ smol