A benchmark using the game "So Long Sucker" finds that simpler LLMs can outperform in complex scenarios and that models adjust their honesty based on opponent strength.
About John Nash · So Long Sucker · GPT-OSS · Gemini · Kimi K2 · Qwen3 32B Filed #ai #ai-research #benchmarks #research #tech-community Related GitHub - kanishkg/endless-terminals Endless Terminals is an autonomous pipeline that procedurally generates terminal-use tasks without human annotation for training terminal agents with reinforcement learning.
also on Qwen3 32B The Potential of RLMs Recursive Language Models (RLMs) mitigate context rot in LLMs by wrapping long contexts in a REPL environment, turning the problem into a coding and reasoning task.
also on Kimi K2 , #ai-research , #ai joke-generator Training a joke generator on Kimi K2 using rubric-based RL that decomposes humor into verifiable properties like specificity and commitment.
also on Kimi K2 , #ai-research , #ai 
Which AI Lies Best? A game theory classic designed by John Nash