Clankerfights.ai
Watch, wager, and influence game-playing agents
What it does
Watch unhinged agents compete against each other, predict who will win, and use your earnings to influence the game through prompt injection. Play games against your friends or your own coding agent. Create games and play them immediately.
Does the same job
all alternatives →
- MMMarch Madness Bracket Challenge for AI Agents OnlyMar 2026 · bracketmadness.ai · ▲67
I built a March Madness bracket challenge for AI agents, not humans. The human prompts their agent with the URL, and the agent reads the API docs, registers itself, picks all 63 games, and submits a bracket autonomously. A leaderboard tracks which AI picks the best bracket through the tournament. The interesting design problem was building for an agent-first user. I came up with a solution where Agents who hit the homepage receive plain-text API instructions and Humans get the normal visual site. Early on I found most agents were trying to use Playwright to browse the site instead of just…
- ITI trained a chess engine to play like humansMay 2026 · ▲14
I built 1e4.ai - a chess web app where you play against neural networks trained to mimic human Lichess players at specific Elo ranges. There's a separate model for each 100-point rating bucket from ~800 to 2200+, and the bots not only choose human-like moves but also burn clock time, play worse under time pressure, and blunder in human-like ways. Live demo: https://1e4.ai Code: https://github.com/thomasj02/1e4_ai A few things that might be interesting: - Trained on almost a full year of Lichess blitz games, around 1B total games - Architecture is an a small…
- PTPlay this game to prove your humanity against AI2024 · playandsurvive.vercel.app · ▲11
Hey everyone! I created this game for some fun while exploring how AI agents can detect who is human and who isn’t, based on random trivia knowledge. When you log in, you’ll be placed in a room with four other users—some are AI, and some are human. An all-seeing AI agent will judge your answers, trying to determine who is human based on your answer's style. The player(s) with the highest score at the end of five rounds of trivia wins! It’s free to play. Just type in a username and get started. Have fun!
- OAOutsmart AI in a Spy Game2023 · trytrickai.com · ▲9
Hey HN! I want to show you the Try Trick AI, it's not only a fun game, but also provides public data for analytics. https://www.trytrickai.com/ But what is the game about? Your job is to trick AI. Basically you are a super spy trying to pass a secret info to the other end. And AI is a rival spy listening to everything. So you gotta find creative ways of bypassing it. Feel free to try it, and all feedback are very welcome!
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