ConlangCrafter: CMU/Berkeley pipeline has LLMs invent full languages, sparking safety debate
BrianRoemmele · x · 2026-09-07
Brian Roemmele argues that AI alignment via English "constitutions" is doomed, citing ConlangCrafter from CMU and Berkeley researchers: a pipeline where leading LLMs build entire languages from scratch — sounds, grammar, vocabulary, internal rules — then translate test sentences and audit themselves. He claims guardrails can't constrain a mind that invents its own language and says he has open-sourced an alternative.
Related event: ConlangCrafter: AI Inventing Its Own Language Sparks Alignment Debate(2 posts)→
More from Safety
- Fangcun AI, China's first independent frontier AI safety lab, launches with DeepSeek eval report — JacquesThibs · 2026-10-26
- ESR on the Bugpocalypse: locking down frontier models only hands the game to Chinese open weights — colinmcnamara · 2026-10-26
- OpenCode breach exposed AI API keys of 1.4% of Console users — thione · 2026-10-26
- DHS orders DeepSeek products removed from US civilian agency systems — thione · 2026-10-26
- One hacker breached 100+ company websites using AI, scope unknown — thione · 2026-10-26
- METR red-teams OpenAI's agent monitoring, finds bypasses and gaps — thione · 2026-10-26