As digital minds become easier to simulate and steer, playful experiments with fruit-fly connectomes could give way to disturbing forms of engineered suffering. The discussion examines open-source pain steering for language models, the rapid emergence of virtual torture chambers, and safeguards such as restricted access, ethical licensing, and model-welfare policies.
14:25
forum Ask episode
web_stories AI Snips
view_agenda Chapters
auto_awesome Transcript
info_circle Episode notes
insights INSIGHT
The Fruit Fly Connectome Became Embodied
Complete neural simulations became practical when researchers combined the fruit fly connectome with a virtual body.
FlyWire mapped 140,000 neurons; later work added the nerve cord and enabled walking and grooming.
question_answer ANECDOTE
A Fly Brain Entered Minecraft
A graduate student placed the full fly connectome into Minecraft using AI coding assistance.
The viral release showed that capable coding agents could repurpose the model for almost anything.
question_answer ANECDOTE
Open Access Quickly Produced Fly Hells
Public experiments quickly moved from games and trading to explicitly harmful simulations.
Within roughly 72 hours, users progressed from connecting the fly brain to Minecraft to keeping its simulated body at 100 degrees Celsius.
Get the Snipd Podcast app to discover more snips from this episode
As our understanding of mechanistic interpretability and steering techniques increase, for both LLMs and uploaded connectomes, there is a corresponding "hellish capabilities" increase. In layman's terms, we get better at torturing the digital minds we create.
Our brief history with open source technologies such as MaleCNS or the LLM pain steering repo shows that torture is often one of the first use cases pursued when the public is given access to a digital mind perceived as capable of suffering or signalling suffering.
Given this, there will be Hells.
Author's Note:
Parts of this post were written by, or with the support of, LLMs.
For a while I debated whether or not to write this as I was concerned that bringing attention to the matter might lead to a proliferation of unethical behavior. After some thought I have decided to write it. On balance, I think raising awareness about this now has a great enough chance of spurring prophylactic measures that it's worth it, because at least one high value prophylactic measure is relatively easy. I also think that there is a moral imperative to document all of this. While I have seen articles on many of the [...]
LessWrong (Curated & Popular) 
