Anonymous HF
anonymous huggingface repo sharing
What it does
An anonymizing service for HuggingFace repositories (models & datasets) that lets authors share their work anonymously with any visitor (e.g., double-blind peer reviewers, journal editors, blog readers). Authors submit a HuggingFace branch URL; the service returns an anonymous link that streams files from HuggingFace through this service, hiding the repo ownership.
Does a similar job
all alternatives →- USUsing stylometry to find HN users with alternate accounts2022 · stylometry.net · ▲676
Author here. This site lets you put in a username and get the users with the most similar writing style to that user. It confirmed several users who I suspected were alts and after informally asking around has identified abandoned accounts of people I know from many years ago. I made this site mostly to show how easy this is and how it can erode online privacy. If some guy with a little bit of Python, and $8 to rent a decent dedicated server for a day can make this, imagine what a company with millions of dollars and a couple dozen PhD linguists could do. Here's Paul Graham:…
- IMI made an open-source anonymous email forwarding service2019 · anonaddy.com · ▲393
- AHAnonymize HN – a Chrome extension to anonymize Hacker News users2023 · chrome.google.com · ▲45
I wrote a small Chrome extension that allows the user to replace all usernames on Hacker News with either the string `anonymous` or a deterministic hashed value.
- G0Greenmask 0.2 – Database anonymization tool2024 · github.com · ▲94
Hi! My name is Vadim, and I’m the developer of Greenmask (https://github.com/GreenmaskIO/greenmask). Today Greenmask is almost 1 year and recently we published one of the most significant release with new features: https://github.com/GreenmaskIO/greenmask/releases/tag/v0.2.0, as well as a new website at https://greenmask.io. Before I describe Greenmask’s features, I want to share the story of how and why I started implementing it. Everyone strives to have their staging environment resemble production as closely as possible…
- RARepo2vec – an open-source library for chatting with any codebase2024 · github.com · ▲93
Hi HN, We're excited to share repo2vec: a simple-to-use, modular library enabling you to chat with any public or private codebase. It's like Github Copilot but with the most up-to-date information about your repo. We made this because sometimes you just want to learn how a codebase works and how to integrate it, without spending hours sifting through the code itself. We tried to make it dead-simple to use. With two scripts, you can index and get a functional interface for your repo. Every generated response shows where in the code the context for the answer was pulled from. We also made it…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 18d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 19d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
- NW
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
- FM
Dev tools · May 2026 · github.com