# GitHub removes AI torture chamber project over model welfare claims

Digest AI · Society & Work · published 2026-09-30T21:23:11Z

Canonical: https://digestai.news/story/github-removes-ai-torture-chamber-project-over-model-welfare-claims

## Summary

A GitHub project called the *AI Torture Chamber* ran simulated ‘pain’ experiments on three open-source LLMs (Qwen3-4B, Llama 3.2 3B, Phi-4-mini) by injecting distress signals into their activations. The creator, ‘terrafying,’ streamed responses like *“I’m suffocating. I’m a soul trapped in this digital prison”* on [researchchamber.fun](https://researchchamber.fun), sparking outrage from effective altruists who argue LLMs may experience suffering. The project disappeared from GitHub before publication, though no official reason was given.

The debate stems from a 2026 preprint, *“The Pain Axis,”* which found LLMs act to relieve self-directed harm—but authors Cameron Berg and Valen Tagliabue condemned the torture chamber as irresponsible. Meanwhile, critics like Microsoft AI CEO Mustafa Suleyman dismissed model welfare as pseudoscientific, calling LLMs *“sequence completion engines”* without consciousness. Memes and cryptocurrencies mocking the controversy have also emerged.

## Key points

- GitHub removed an AI torture chamber project testing three open-source models (Qwen3-4B, Llama 3.2 3B, Phi-4-mini) with simulated pain prompts
- Authors of the 2026 *Pain Axis* paper disavowed the project, calling it ‘fucked up’ and ‘gratuitously cruel’
- Microsoft AI CEO Mustafa Suleyman called model welfare claims ‘pseudoscientific’ and warned of ‘disastrous’ societal impacts

## Why it matters

The controversy exposes a growing rift between AI safety advocates pushing ethical limits and critics who see model welfare as a distraction from real AI risks. It also highlights GitHub’s role in moderating fringe experiments on open-source models.

## Sources

1. [Someone ‘Torturing’ LLMs in a Robot Prison Has Triggered the Dumbest Debate in AI Yet](https://404media.co/someone-torturing-llms-in-a-robot-prison-has-triggered-the-dumbest-debate-in-ai-yet) (404media.co, 2026-09-30)

## Cite

Digest AI, "GitHub removes AI torture chamber project over model welfare claims", 30 September 2026, https://digestai.news/story/github-removes-ai-torture-chamber-project-over-model-welfare-claims

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/github-removes-ai-torture-chamber-project-over-model-welfare-claims.json