Steganographically encode messages with LLMs and Arithmetic Coding
Good morning HN! For a while now I have been toying with this idea and now finally have a working prototype. This project allows you to encode secret messages into ordinary looking text by using arithmetic coding with a probability model derived from an LLM. By encrypting the message and then decompressing the encrypted message using the arithmetic coder, you get output which looks just like randomly sampled output from the LLM. Except, it actually encodes your secret messages in the specific choices of tokens. By using authenticated encryption, only a user who knows the key can know that a…
In plain words
This project enables users to hide encrypted messages within seemingly normal text generated by language models through arithmetic coding. The technique combines LLM probability models with encryption to embed secret data into token sequences, making hidden messages appear as ordinary AI-generated text to observers. Only recipients with the correct key can detect and decrypt the messages. This approach allows covert communication through public channels without revealing that a secret conversation is occurring.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Good morning HN! For a while now I have been toying with this idea and now finally have a working prototype. This project allows you to encode secret messages into ordinary looking text by using arithmetic coding with a probability model derived from an LLM. By encrypting the message and then decompressing the encrypted message using the arithmetic coder, you get output which looks just like randomly sampled output from the LLM. Except, it actually encodes your secret messages in the specific choices of tokens. By using authenticated encryption, only a user who knows the key can know that a message is present. To others, the messages appear almost indistinguishable from typical LLM output. This technique allows you to hide your secret messages in a public channel without other users even knowing that a secret conversation is taking place. For example, the prototype is instructed to output text which could plausibly look like a tweet on Twitter. This allows you to post your secret messages in an accessible public space without being discovered. This could be beneficial for situations where users don't want to draw suspicion for using encrypted messaging, such as if they are trying to avoid state-sponsored spying. On the other hand, a potentially nefarious use of this technology could be the sharing of botnet command-and-control messages. By taking advantage of a technology like this, the messages could be shared in a public space where they could be widely distributed without an effective way to detect or block them. This project is at an early stage and any feedback or contributions are welcome! Thanks for reading, Shawn
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 · 16d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d 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 · 26d ago · cactuscompute.com
Launched alongside, February 2025
the whole month →
Screen Studio 3.0▲1,833Beautiful screen recordings with instant shareable links
Growth · 2025 · screen.studio
- IG
I was at FB/Meta from late 2013 to early 2023, mostly working in the compiler/runtime spaces. I got hit in the spring 2023 layoff wave. I immediately started making games in my newfound free time (a lifelong interest, and I even worked in AA(A?) back ca. ~2000), and in October 2023 I stumbled upon the idea of a roguelike pachinko/plinko game inspired by Luck Be A Landlord. Things snowballed quickly, I started talking to publishers, then worked like crazy through all of 2024, almost the hardest I've ever worked in my career, and launched the game in December 2024. It's sold…
Work · 2025
- IB
i wanted to change the habit of reaching for my phone in the morning and doomscrolling away an hour so i built an app to help me. now i have to literally touch grass before accessing my most distracting apps the app is built in swiftui, uses the screen time apis provided by apple and google vision to recognise grass or not i'd love to get your thoughts on the concept.
Life & fun · 2025 · touchgrass.now