writing
Just a moment...
journals.aom.orgalignment rule breaking
How I don't use LLMs
gleech.org
better murder prompt · anthropic-experimental/agentic-misalignment@8562ad7
github.com
Ingressing Minds: Causal Patterns Beyond Genetics and Environment in Natural, Synthetic, and Hybrid Embodiments – Levin (2025)
Michael Levinstream.syscoi.com
alignment / patterns in worlds
What I've learned about writing AI apps so far | Seldo.com
seldo.com50 things I know
usefulfictions.substack.com
> We find that LLMs’ intelligence [...] almost linearly correlates with their ability to compress external text corpora
> compression efficiency [...] serves as a reliable evaluation measure that is linearly associated with the model capabilities
IQ for LLMs just dropped https://t.co/B9UOeLctRS