Infinite Swap – Trade a bottle cap up to a house
Hey HN, Infinite Swap is a game inspired by Kyle MacDonald’s One Red Paperclip and other bigger-and-better swap stories - you start with a green bottle cap and trade it with other characters in various locations all the way up to a house and beyond. A while ago I got inspired by viral games Infinite Craft and What Beats Rock? and wanted to make my own ‘exploring a LLM’s latent space’ style challenge. After much experimentation this became a trading style game, where the LLM comes up with all the items, trading scenarios and value estimates, which ended up being surprisingly fun and somewhat…
What it does
In the maker’s words, at launch
Hey HN, Infinite Swap is a game inspired by Kyle MacDonald’s One Red Paperclip and other bigger-and-better swap stories - you start with a green bottle cap and trade it with other characters in various locations all the way up to a house and beyond. A while ago I got inspired by viral games Infinite Craft and What Beats Rock? and wanted to make my own ‘exploring a LLM’s latent space’ style challenge. After much experimentation this became a trading style game, where the LLM comes up with all the items, trading scenarios and value estimates, which ended up being surprisingly fun and somewhat of a roller coaster to play. I found it was the most intriguing if I separated the item offer from its valuation - so I implemented a pricing oracle called “Sal” who gives this info with his, sometimes snarky, opinion after each trade. The item offer mechanism goes deeper too - each character’s profile is combined with a set of hidden motivations. I then use embeddings and cosine similarity to represent the desire the character has for the player's item, and therefore what they are willing to offer in exchange. Links to play: iOS (small number of ads, polished): https://apps.apple.com/us/app/infinite-swap/id6761694545 Android (small number of ads, polished): https://play.google.com/store/apps/details?id=com.squizsoftw... Web (no ads, a touch rougher than the mobile versions but still very functional): https://infiniteswap.app Stack: GPT-4.1-mini for item generation, SDXL Lightning for item images, Kokoro for voices (the latter two running on my 4090 at home). Postgres + FastAPI on k3s for the backend, native Swift/Kotlin for mobile, React for web. Keen for any feedback, bug reports, improvement suggestions, etc. I’ll be around for a few hours if you have any questions. Daniel
Does the same job
all alternatives →
- STSwapidy: Trade up your old stuff for new stuff2013 · swapidy.com · ▲29
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 · 17d 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 · 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