AI article
Giving an Open-Weight Language Model the Vote in Among Us Meetings
Community description: I let gpt-oss:20b play every seat in my Among Us meetings and compared it with the small trained networks that otherwise vote. It never did better: alone, the crew won 2 of 16 games against 52.0%, and with the network's guesses in its prompt it matched it once and fell short four times.
Dev.to | Oct 16, 2026 | Seth Wheeler
Automated excerpt
The model is gpt-oss:20b, an open-weight model from OpenAI, running locally through Ollama. On its own the language model did much worse than the networks. The networks' votes need no model calls at all.
Selected automatically from source text; not independently written or fact-checked. Read the original for full context.