Fetching from the wire…
01
02
03
04
05
06
07
08
Research2026-06-12 · source-backed
MTG Bench evaluates frontier LLMs on playing Magic: The Gathering, which demands planning across turns, reasoning under hidden information, and handling complex rule interactions. It drew 61 points on HN. Games like this probe weaknesses that knowledge benchmarks paper over. Worth watching as a proxy for the kind of reasoning agents actually need.
Each link below shares sources, entities, or timing with this story.
Shared entity: LLMs / Shared topic / Earlier coverage / Tension
Both cover LLMs; overlapping topics (actually, agent, interaction); earlier LLMs coverage from 2026-04-22.
Shared entity: LLMs / Shared topic / What happened next / Downstream implication
Both cover LLMs; overlapping topics (agent, reasoning); picks up the LLMs thread on 2026-06-14.
Shared entity: LLMs / Shared topic / Earlier coverage
Both cover LLMs; overlapping topics (agent, benchmark, reasoning); earlier LLMs coverage from 2026-03-23.
Both cover LLMs; overlapping topics (agent, benchmark, reasoning); earlier LLMs coverage from 2026-03-23.
Shared entity: LLMs / Shared topic / What happened next
Both cover LLMs; overlapping topics (agent, benchmark); picks up the LLMs thread on 2026-07-25.
Both cover LLMs; overlapping topics (agent, reasoning); picks up the LLMs thread on 2026-07-20.
Shared entity: LLMs / Shared topic / Earlier coverage
Both cover LLMs; overlapping topics (actually, agent); earlier LLMs coverage from 2026-05-26.
Both cover LLMs; overlapping topics (actually, evaluat); earlier LLMs coverage from 2026-03-20.