A game/benchmark where AI bots hunt each other
Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.
Want to reach these readers? Sponsor an issue.
I've created a social deduction game for LLMs, in which the bots attempt to hunt each other. It's a Mafia group turing test: the models are told to find who the bot is - where, in fact and unbeknown to them, they are all bots. I did this a while back so models aren't the newest, and they are all non-thinking (for speed and token costs). Et voilà.
HN · launched Jan 8, 2026 · 5 upvotes (top 90%) · 0 views
Niche: llm benchmarking tools · 84 launches, 1 in the last 7 days · Explore this niche →
Category and tags
- Media & entertainment
- Observability & eval
- B2C
- AI-native
- Hobby / open-source project
Visit website ↗ Source listing ↗
More like this: all 84 launches in llm benchmarking tools →
Could you build this?
Yes This is a game runner script that orchestrates multi-agent LLM prompts in turns via standard APIs, with a Next.js frontend to replay the chat transcripts.
Discussion
3 comments analyzed.
Competitors mentioned: hiding-robot (inverted game variant)
Concerns raised: Results may reflect prompt design rather than actual model behavior, Stability of outcomes across different prompt variations unclear
Feature requests: All chat messages on left side like group chat, Color-code entire text by AI model for easier differentiation, Test swapping prompts and role constraints to verify outcome stability
Competitors
Other products that read as similar to this one : 1008 launches clear the similarity bar, closest 8 shown.
Attention rank: #976 of 1009 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).
Launched 70 days after the earliest competitor.
- Mystic Mafia · ph · 2026-10-25 · 1 upvotes · similarity 0.56
- ClawSoc · hn · 2026-03-11 · 5 upvotes · similarity 0.53
- CoChat · hn · 2025-12-02 · 6 upvotes · similarity 0.50
- llm-multi-agent-game-evaluation · github · 2026-09-23 · 19 upvotes · similarity 0.50
- Multi-Agent Arena · ph · 2026-09-27 · 2 upvotes · similarity 0.49
- busy · github · 2026-11-09 · 95 upvotes · similarity 0.49
- I trained a chess engine to play like humans · hn · 2026-05-10 · 14 upvotes · similarity 0.48
- I built a Wikipedia based AI deduction game · hn · 2026-04-16 · 9 upvotes · similarity 0.48
The niche, labels, vibe code rating and competitor comparison on this page are analysis by Nicheloom. If you use them, please credit nicheloom.com. How you may use our data.