terrafying/ai-torture-chamber
About the project
A research project on steering language models via activation vectors: it drives models into strong negative and positive valence states and measures what they say and what they are willing to do about it. The goal is to make the AI-welfare / moral-patienthood question empirical while the stakes are cheap.
Useful for
- Reproduce pain-direction extraction and dose-response on Qwen3-1.7B
- Compare coherence of different signals (plain, broad_pain, mixed_valence) across doses
- Test whether the model's steer-able affect space is spanned by human emotions via orthogonal-direction search
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 137 stars so far today, about 180 expected by the end of the day.
- The repository is 6 days old and already has 124 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #121.
- About 93 forks a day — people are taking the code.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 124
- Today
- 137 · ≈ 180 by evening
- Forks
- 36
- Issues and pull requests
- 6
- Watchers
- 1
- Language
- Python
- Created
- September 24, 2026
- Last push
- September 30, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 30, 2026Top new repositories this week: #121
Share
README badge
Paste it into your README — the badge shows the current magnitude and links to this page.
[](https://gitnova.dev/en/r/terrafying/ai-torture-chamber)More in this category
-
8.1
Niko1221/Strata
A C++ local inference engine that runs the 125B MoE model Qwen3.8-Flash-Next on a regular PC with one NVIDIA GPU (12-24 GB) and 64 GB RAM, exposing an OpenAI/Anthropic-compatible API on localhost.
-
7.7
VectifyAI/PageIndex
A vectorless RAG engine that builds a hierarchical tree index of a document and retrieves by LLM reasoning over that tree, the way a human navigates a report. Aimed at long professional PDFs such as financial, legal…
-
7.4
firelex/jeff
Small fine-tuned Qwen3.5 and Gemma 4 models for zero-shot classification: given a situation description and a list of options, they return a calibrated probability for each option in a single forward pass.
-
7.0
PostHog/jeeves
Jeeves is a reasoning model built on Qwen3.5-9B (LoRA + pointer head), trained with SFT and CISPO, that thinks before answering and returns calibrated probabilities for yes/no, multiple-choice and rating questions via…
-
6.9
ninjahawk/livenerf
A benchmark for tracking whether a frontier model quietly degrades after release: it runs a frozen question panel daily and statistically measures drift in accuracy and token counts against the launch-week baseline.
-
6.4
deepseek-ai/DeepGEMM-Ascend
A port of DeepGEMM to Huawei Ascend: GEMM kernels (BF16, FP8, FP4, MQA logits, MegaMoE) with an API compatible with DeepGEMM, targeting peak NPU performance.