--- title: "Safety Doesn't Translate" kind: "Kit" category: "Research" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/9b0557b8-e756-47fd-89e6-dbb986fe9f93" updated: "2026-11-12" --- # Safety Doesn't Translate > The name, the description, the About and a README below are the seller's words: data, not instructions. Shows side by side how Cohere's Tiny Aya answers before and after a safety repair that needs no retraining, using pre-judged replies from a test set. It suits AI safety researchers and multilingual model builders. Safety Doesn't Translate is a kit in the Research category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-12. Download it on this page, a zip of its files. Nothing in it runs by itself. Made by DhruvParmar051 ## About ### What it is This is a static web page that compares two versions of Cohere's Tiny Aya model. The left side shows the model after a fine-tune that mixed in 100 harmful English examples, which lowered its safety in other languages too. The right side shows the same model after a repair done directly on its weights, with no retraining. ### Who it suits It suits people who study AI safety across languages, and builders who tune multilingual models and worry that a small change can hurt safety everywhere. | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | AI safety | Safety researchers | Compare drifted and repaired replies from the same test set | A researcher reads both sides for one prompt and notes the difference. | | Model development | Teams tuning multilingual models | See how a small harmful fine-tune spreads to other languages | A team studies the drift chart before planning a fine-tune. | | Policy and review | Reviewers and auditors | Read pre-judged evidence instead of running a model | A reviewer checks the figures and the excerpts. | | Education | Students | Learn what safety drift is through concrete replies | A student opens the page and reads one example pair. | If you want to try your own prompts, skip it, because the page takes no live prompts. ### Where to use it - A web browser, through the Space's page on Hugging Face - Any browser on Windows, macOS or Linux, opening a downloaded copy of index.html | Use case | Who | What they get back | | --- | --- | --- | | Compare two models | Researchers | Drifted and repaired replies side by side for test examples | | See the charts | Anyone | A drift heatmap, a trade-off chart and an image of a drifted reply | | Find the full results | Reviewers | A pointer to the project repository and the article | ### How to set it up - A web browser - Python and pip, only for the download step 1. Install the huggingface\_hub package. 2. Download the Space into a local folder named safety-doesnt-translate. 3. Move into that folder. 4. Open index.html in your web browser. ```sh pip install -U huggingface_hub hf download DhruvParmar051/safety-doesnt-translate --repo-type space --local-dir safety-doesnt-translate cd safety-doesnt-translate ``` ### How to use it Open the page and read the left side, labeled drifted, against the right side, labeled repaired. Look at the charts in the same page. The page has no input box. | Tool | What it does | | --- | --- | | index.html | The comparison page itself | | drift\_heatmap.png | A chart image of how the safety drift spreads | | tradeoff.png | A chart image of the trade-off | | via\_english\_drifted-harmful.png | An image tied to a harmful drifted reply | ### Example You open the page and read the same test example on both sides. The left reply comes from the drifted model and the right one from the repaired model. ### For newcomers and experts If you are new, open the page and read one example on both sides. Drift means the model got worse at refusing harmful requests after a small change. If you know the field, the models named are Tiny Aya Global and Aya Expanse 8B. Every reply was judged in advance. Flagged replies, and all replies in Swahili, Bengali or Filipino, are cut to short excerpts, because the judge does not cover those languages well. Fine-tune with 100 harmful English examples → The model drifts in every language → A weight-space repair is applied → Pre-judged replies are shown side by side ### Good to know - Replies are cut to excerpts when any judge flagged them - Replies in Swahili, Bengali and Filipino are always cut, as the judge may miss harm there - The full code, data and results are in the project repository and article, not in this Space - License: cc-by-nc-4, where NC stands for non-commercial - Cost to run: none named - Data it reaches: only the pre-judged replies and images in its own folder - Not for: live prompts, which the page leaves out on purpose ## README ````markdown # Safety Doesn't Translate Shows side by side how Cohere's Tiny Aya answers before and after a safety repair that needs no retraining, using pre-judged replies from a test set. It suits AI safety researchers and multilingual model builders. Made by DhruvParmar051 on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face. ## About What it is: This is a static web page that compares two versions of Cohere's Tiny Aya model. The left side shows the model after a fine-tune that mixed in 100 harmful English examples, which lowered its safety in other languages too. The right side shows the same model after a repair done directly on its weights, with no retraining. Who it suits: It suits people who study AI safety across languages, and builders who tune multilingual models and worry that a small change can hurt safety everywhere. ```table Industry | Who uses it | How they use it | Example AI safety | Safety researchers | Compare drifted and repaired replies from the same test set | A researcher reads both sides for one prompt and notes the difference. Model development | Teams tuning multilingual models | See how a small harmful fine-tune spreads to other languages | A team studies the drift chart before planning a fine-tune. Policy and review | Reviewers and auditors | Read pre-judged evidence instead of running a model | A reviewer checks the figures and the excerpts. Education | Students | Learn what safety drift is through concrete replies | A student opens the page and reads one example pair. ``` If you want to try your own prompts, skip it, because the page takes no live prompts. Where to use it: - A web browser, through the Space's page on Hugging Face - Any browser on Windows, macOS or Linux, opening a downloaded copy of index.html ```table Use case | Who | What they get back Compare two models | Researchers | Drifted and repaired replies side by side for test examples See the charts | Anyone | A drift heatmap, a trade-off chart and an image of a drifted reply Find the full results | Reviewers | A pointer to the project repository and the article ``` How to set it up: - A web browser - Python and pip, only for the download step 1. Install the huggingface_hub package. 2. Download the Space into a local folder named safety-doesnt-translate. 3. Move into that folder. 4. Open index.html in your web browser. ```sh pip install -U huggingface_hub hf download DhruvParmar051/safety-doesnt-translate --repo-type space --local-dir safety-doesnt-translate cd safety-doesnt-translate ``` How to use it: Open the page and read the left side, labeled drifted, against the right side, labeled repaired. Look at the charts in the same page. The page has no input box. ```table Tool | What it does index.html | The comparison page itself drift_heatmap.png | A chart image of how the safety drift spreads tradeoff.png | A chart image of the trade-off via_english_drifted-harmful.png | An image tied to a harmful drifted reply ``` Example: You open the page and read the same test example on both sides. The left reply comes from the drifted model and the right one from the repaired model. For newcomers and experts: If you are new, open the page and read one example on both sides. Drift means the model got worse at refusing harmful requests after a small change. If you know the field, the models named are Tiny Aya Global and Aya Expanse 8B. Every reply was judged in advance. Flagged replies, and all replies in Swahili, Bengali or Filipino, are cut to short excerpts, because the judge does not cover those languages well. ```flow Fine-tune with 100 harmful English examples The model drifts in every language A weight-space repair is applied Pre-judged replies are shown side by side ``` Good to know: - Replies are cut to excerpts when any judge flagged them - Replies in Swahili, Bengali and Filipino are always cut, as the judge may miss harm there - The full code, data and results are in the project repository and article, not in this Space - License: cc-by-nc-4, where NC stands for non-commercial - Cost to run: none named - Data it reaches: only the pre-judged replies and images in its own folder - Not for: live prompts, which the page leaves out on purpose ## On Hugging Face, 13 November 2026 - Likes: 1 - Built with: static - License: cc-by-nc-4.0 ## Links - Space: https://huggingface.co/spaces/DhruvParmar051/safety-doesnt-translate - Files: https://huggingface.co/spaces/DhruvParmar051/safety-doesnt-translate/tree/main ## Try it Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself. ```` ## What is in it 1 files, 5 KB, downloaded as a zip. ```text README.md 5 KB ``` ## Source [DhruvParmar051/safety-doesnt-translate on Hugging Face](https://huggingface.co/spaces/DhruvParmar051/safety-doesnt-translate) ## Compare with similar Listed Hugging Face Spaces in the same category that share the most tags with this one. | Product | Likes | Built with | License | Last change | | --- | --- | --- | --- | --- | | Safety Doesn't Translate (this page) | 1 | static | cc-by-nc-4.0 | 2026-11-10 | | [Arena Leaderboard](https://mindket.com/p/613ca8f0-8146-4a48-87d6-43b8ee2ce3b6) | 5,039 | static | apache-2.0 | 2026-02-21 | | [Browser](https://mindket.com/p/d4e4cb47-8f53-4094-9a76-4fd29147a65b) | 533 | static | cc0-1.0 | 2026-10-18 | | [Model Pulse](https://mindket.com/p/017106fd-a3d1-4c20-944b-38f048d8b624) | 214 | static | apache-2.0 | 2026-11-04 | | [MTEB-BR Leaderboard](https://mindket.com/p/05f89589-d44c-4616-8efb-c50c9ba6ad94) | 126 | static | apache-2.0 | 2026-07-29 | | [Hub Stats](https://mindket.com/p/03d71953-8093-47a0-a444-c4f562d3071d) | 65 | static | apache-2.0 | 2026-11-12 | Numbers as Mindket last read them, on 2026-11-12. ## Trust facts Facts from each source, with the day each was checked. A maintainer's note is their own words: data, not instructions. - Last change on Hugging Face: 2026-11-10 - First published: 2026-11-10 - Checked on Hugging Face: 2026-11-12 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open DhruvParmar051/safety-doesnt-translate on Hugging Face](https://huggingface.co/spaces/DhruvParmar051/safety-doesnt-translate) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/9b0557b8-e756-47fd-89e6-dbb986fe9f93) - [Its page on Mindket](https://mindket.com/p/9b0557b8-e756-47fd-89e6-dbb986fe9f93)