you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
this post was submitted on 09 Aug 2026
13 points (93.3% liked)
TechTakes
2639 readers
64 users here now
Big brain tech dude got yet another clueless take over at HackerNews etc? Here's the place to vent. Orange site, VC foolishness, all welcome.
This is not debate club. Unless it’s amusing debate.
For actually-good tech, you want our NotAwfulTech community
founded 3 years ago
MODERATORS
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