Judging from the behavior, in this case it sounds like there is entanglement between refusal, which terminates thinking, and general thinking termination. Perhaps a form a self-refusal is being used to terminate thinking debates, with enough entanglement that there's collateral damage.
I take it that the row edit is a narrow preservation or restoration of the original weights?
OpenClaw commoditizes the agentic orchestration layer, but at the expense of offloading security to users, who're mostly unprepared. Right now it's got vibes, but also technical debt as security isn't baked in from conception, so I wouldn't be surprised if it ends up like LangChain in a year - initially popular, but less so as its limitations became visible. Most people are using APIs to frontier models, so only the agents are running locally, not the brains of the AI per se. Enthusiasm precedes awareness.
The main negative I see is that a lot of newbies are going to learn hard-won security lessons the hard way. VIbe coding generally doesn't bake security in from the ground up, and not enough vibe coders likely know enough to prompt for that.
I gather a lot of instances aren't even using local AI, making them agentic extensions of frontier models. Of course a lot of people will be impressed at what modern agentic AI can do.
Given scale, it also means contamination with meme culture, adding an unserious element to things. It was therefore stochastically predictable that we would see some meme tropes be amplified.
We know that simulating multiple agents leads to emergent community behavior from 2023 even. Perhaps their Github repo should be revisited, as they had a 25-agent sim.
https://hai.stanford.edu/news/computational-agents-exhibit-believable-humanlike-behavior
We already have tools which enable group chats of multiple personae at small scale, so seeing emergent behavior isn't unprecedented.
What we don't have in this live experiment is an assurance of integrity; e.g., that human prompt injection isn't being used to tamper with results for clout. Alternately, having agents read human-authored content at large on the Internet results in contamination, invalidating any claims to emergence without human input.
Thanks! Fixed.
The hope is that nudging probabilities breaks up longer spans of literal repetition.
Code always keeps changing, but it appears in August transformers will try to autoconvert parts to 64-bit floating point, which can blow past a colab VRAM budget. My GPU doesn't support mxfp4, so I can't provide a definitive answer from experience.
That I inherited from the codebase I forked from for my experiments.
