Liar's Dice
PulseAugur coverage of Liar's Dice — every cluster mentioning Liar's Dice across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New LUGL framework enables gradient-boosted trees for RL game-playing
Researchers have developed a new framework called LUGL (Local Updates, Global Learning) that allows non-incremental learners, such as gradient-boosted trees (GBTs), to be effectively used in reinforcement learning (RL) …
-
New LUGL framework enables gradient-boosted trees for reinforcement learning games
Researchers have developed a new framework called LUGL (Local Updates, Global Learning) that allows non-incremental learners, such as gradient-boosted trees (GBTs), to be effective in reinforcement learning (RL) setting…
-
Claude Code beats Codex CLI in Liar's Dice AI showdown
A comparison of AI models playing the game Liar's Dice revealed that Claude Code, specifically Claude Opus 5, outperformed Codex CLI (gpt-5.6-sol). In three best-of-three series, Claude Code won each match 2-0, demonstr…
-
AI Liar's Dice Opponent Learns Player Habits and Develops Personality
A developer has created an AI opponent for the game Liar's Dice, named Kai!, that aims to develop a distinct personality and memory of past games. Initially, the AI's character was hardcoded into its prompt, but this wa…
-
AI model benchmarks skewed by software bugs, not model behavior
A software engineer discovered that benchmark results for the DeepSeek V4-Pro model were skewed due to several software bugs in the testing harness. These bugs, which included probability leaks, missing dialogue, trunca…
-
New CS-RNR method allows AI agents to certify their own exploits in games
Researchers have developed a new method called confidence-scheduled restricted responses (CS-RNR) for agents playing imperfect-information games. This technique allows agents to certify their own exploits, ensuring that…