Trainable Langton's ant borrows from NCA architecture, dubbed Mordvintsev's ant
max_romana · x · 2026-08-14
ilzhechev tweets about a trainable version of Langton's ant, borrowing from NCA architecture, and jokes about calling it Mordvintsev's ant. Related to ALIFE 2026 and ERA Workshop.
More from Research
- Steerling-8b Breaks Assumption: Larger Models Can Be More Interpretable — juliusadml · 2026-08-14
- LLM Architecture: How Large Vocabularies Mitigate Softmax Rank Bottlenecks — kalomaze · 2026-08-14
- Counterintuitive Finding: Visual Reasoning Relies on Tool-Call Text, Not Pixels — kwangmoo_yi · 2026-08-14
- Study: Skipping Images for Tool Calls Improves Visual Reasoning — kwangmoo_yi · 2026-08-14
- Goodfire Co-founder on AI Interpretability and Tackling Agent Reward Hacking — mathildepapillo · 2026-08-14
- Reverse-Engineering Claude's Tokenizer: Smaller Vocab but Higher Inference Cost — kalomaze · 2026-08-14