RepoAlerts

ValerioDolci/frontier-weight-edit

Can I trust it?

No red flags in our checks.

  • Stars from real accounts No data

    We haven't checked its stars for fakes yet.

  • Active OK

    Last change 7 days ago.

  • Licence OK

    MIT: you can use it for free, also in a commercial product. Keep the licence notice.

Quick checks from public data. They help, but they are no guarantee.

From the GitHub description

A frontier model edits another model's weights by hand (Gemma 4 12B, EN->IT tense). Plus an awareness experiment: tampering Qwen3.8-27B into a hidden brand preference with 0.06% of its weights.

We haven't written this repo up yet. It gets a summary once it enters the radar's top.

How to use it

Ask your AI to set it up

Paste this into Claude, ChatGPT or your coding assistant.

Help me install and set up ValerioDolci/frontier-weight-edit in my project. Follow its README: https://github.com/ValerioDolci/frontier-weight-edit. Explain each step and check it is safe before running anything.

Read the README

Star curve

35From 0 to 35 stars between 3 Nov 2026 and 15 Nov 2026.

Get alerts for repos like this

We'll email you when something in Models & inference starts rising. Free, once a week, only what matches.

What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy

For maintainers

Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.

[![ValerioDolci/frontier-weight-edit on RepoAlerts](https://repoalerts.com/badge/ValerioDolci/frontier-weight-edit.svg)](https://repoalerts.com/repo/ValerioDolci/frontier-weight-edit?ref=badge)
Share on X

  • fujc683/seedance-2-5-flash-reference-video

    A guide to controlling motion in Seedance 2.5 Flash video generation, using a first frame (reference_image) or a motion reference clip (reference_video). It includes an image-to-video API example, pro

    ResourceModels & inference196 stars · +196 this week · 1 day old

  • HybridRobotics/supermimic

    Implements SuperTrack, a supervised learning approach for motion tracking of physically simulated characters. Trains world models and policies to mimic motion data, with generalized and maximal coordi

    AgentModels & inferencePython · 1,736 stars · +1,707 this week · 7 days old

  • hyperionaidev/smolmaxxing

    A research project that runs large language models on low-power devices such as TV boxes and old tablets. It patches llama.cpp with custom kernels, reduced memory use and expert weights streamed from

    Models & inferenceC · 939 stars · +939 this week · 13 days old · HN 483 pts

  • n4ze3m/tiny-voca

    A 4.5M-parameter English text-to-speech model with two voices (F2 female, M2 male) at 24 kHz. Trained from scratch, it runs on CPU, in PyTorch, ONNX Runtime, or in the browser, and can be exported to

    ModelModels & inferencePython · 673 stars · +673 this week · 3 days old

  • NVIDIA/cuPotential

    A CUDA-X library for efficient computation of molecular interactions from standard molecular dynamics forcefields. Provides an OpenMM plugin with nonbonded forces, an integrator and a barostat backed

    LibraryModels & inferencePython · 91 stars · +91 this week · 28 days old

  • WollyMonjac/Tiny-2.1

    A small question-answering transformer written in Turbo C 2.0 that runs under plain DOS on a Pentium or 486DX. It has about 367,000 parameters with 8-bit weights, is trained on roughly 3,500 facts, an

    ModelModels & inferenceC · 200 stars · +200 this week · 2 days old