Athena Crisis AI Uses Pathfinding, K-means, and Greedy Actions Instead of LLMs
Delahuntagram · x · 2026-08-04
This is a link post to the same long-form note about building Athena Crisis’s AI.
- The AI is a conventional game-playing system, not an LLM.
- It uses the game’s pathfinding, k-means clustering, and greedy action selection.
- The design is intentionally mostly deterministic and stateless, which improved testability and made it easier for players to adapt.
- The author also describes optimizing runtime from 2–3 seconds per turn to more than 10x faster so computation can finish during animations.
- After months of tuning, players ultimately rated it the best AI in its genre.
Related event: Y Combinator to Host Student Hiring Day on August 15(2 posts)→
More from Research
- AI paper argues best-of-K boosts generative expressivity, not just sampling quality — anshulkundaje · 2026-08-04
- ASCII art may be a better taste benchmark for frontier models than you think — weswinder · 2026-08-04
- A curated reading list for DeltaNet, FlashKDA, vLLM serving and MoE — austinvhuang · 2026-08-04
- AI index steepens 5x after late 2024 as compute shifts from pretraining to inference — ProfBuehlerMIT · 2026-08-04
- Free app teaches LLM basics and trains a small model locally on Apple MLX — dr_cintas · 2026-08-04
- Pure VLAs may not need long-horizon planning if VLMs can cover it — m_wulfmeier · 2026-08-04