# laplacesscissors

> laplacesscissors is an open-source AI tool for developer tools. Rust/GPU tool that rotates an LLM's output matrix to keep correct answers and repair wrong. It is available on Linux, CLI and self-hosted.

- **Kind:** Tool
- **Pricing:** Open source
- **Platforms:** Linux, CLI, self-hosted
- **Repository:** https://github.com/miyamoto-renya/laplacesscissors
- **Categories:** [developer tools](https://ai-powered.com/categories/developer-tools)
- **Listing updated:** 2026-11-18

## About

The README says the project takes a pretrained language model's output (readout) matrix and rotates it so that answers already produced correctly stay fixed while answers that fail on a set of expected-answer cases are adjusted. Model loading, tokenization, execution and result storage are handled in Rust, with a Python bridge used for Triton compilation and CUDA or HIP kernels running the GPU work.

The workflow is driven by a command-line interface with subcommands for fetching and inspecting a model, probing weak discrimination directions, diagnosing outputs against expected answers, generating text with an original or edited model, exporting an edited checkpoint, and running scaling analysis across a series of checkpoints. Edits are stored as proposal files that can be reapplied later after checking file hashes.

The project targets researchers and engineers who work with open-weight models on their own GPU hardware and want to study or make targeted post-training output edits. It is distributed under the MIT License, and model checkpoints remain under their publishers' own licences.

## Features

- **Protected readout rotation:** Computes a rotation of the output matrix that aims to keep protected answers unchanged while altering failed ones.
- **Answer-level case format:** Accepts JSONL test cases with a prompt, a list of choices and the index of the correct choice.
- **GPU candidate validation:** Checks candidate edits on the GPU against full-vocabulary margins and protected-output tolerances before accepting them.
- **Checkpoint export:** Writes an edited model as a new checkpoint with a materialization report recording hashes and weight-change norms.
- **Reproducible proposals:** Saves proposal files with hashes for weights, configuration and tokenizer so edits can be reapplied and verified.
- **Scaling analysis:** Runs the same edit policy across a manifest of model sizes and reports loss curves and recovered deviation.

## Good for

- Test whether specific wrong answers of an open-weight model can be corrected by an output-layer rotation
- Study weak discrimination directions in a model's hidden states using numerical probes
- Export an edited checkpoint for downstream evaluation with a recorded provenance report
- Compare how an edit policy behaves across a series of model scales

## FAQ

### What license is it released under?

The README says the project is distributed under the MIT License. Model checkpoints keep the licences set by their original publishers.

### What hardware does it need?

The README requires a Rust toolchain, a Python environment that can import Triton 3.8, and a CUDA or HIP driver. Backend and device are selected with environment variables.

### Which model inputs are accepted?

Hugging Face model IDs with an optional revision, Hugging Face model URLs, or local safetensors model directories. Hub inputs are pinned to a commit SHA.

### Where should questions and bug reports go?

The README directs reproducible bugs to the project's Issues page and questions or research ideas to its Discussions page.

### Is laplacesscissors free?

Yes. laplacesscissors is open source, so you can use and self-host it for free.

### What are the best alternatives to laplacesscissors?

The closest alternatives to laplacesscissors are Tensward, spaceship, TrnRT, Werkbank and Aiproxy.

## Where this comes from

- Description: written from the project's README.

## Alternatives

- [Tensward](https://ai-powered.com/tools/tensward): Tensward is an open-source AI tool for developer tools.
- [spaceship](https://ai-powered.com/tools/spaceship): spaceship is an open-source AI tool for developer tools.
- [TrnRT](https://ai-powered.com/tools/trnrt): TrnRT is an open-source AI tool for developer tools.
- [Werkbank](https://ai-powered.com/tools/werkbank): Werkbank is an open-source AI tool for developer tools.
- [Aiproxy](https://ai-powered.com/tools/aiproxy): Aiproxy is an open-source AI tool for developer tools.

---
Source: https://ai-powered.com/tools/laplacesscissors
