Weekly links Mon Sept 7, 2026
Personal update: I've joined Kairos!
Here are the 3 most interesting and useful things I read (or in one case, listened to) this week:
Evaluating LLM-generated flashcards — Memory Machines
Why frontier LLMs still fail at spaced-repetition flashcards: prompting, fine-tuning, RL, and grounded evaluation across 1,500 labeled flashcards.
Ajeya Cotra – Inside the OpenAI agent swarm that hacked Hugging Face
"This might be the clearest warning shot we ever get."
Absurd Adventure And Amygdalectomy Advocacy
A guest post by Daniel Böttger
Don't miss what's next. Subscribe to Julian Moncarz: