On the (in?)feasibility ontology-based educational question generation with an LLM 0 keet.wordpress.com · 21d · discuss
Anthropic tells investors quarterly revenue up nearly 50% to $16.8bn ahead of IPO 0 simonwillison.net · 21d · discuss ·
SWE-bench Multimodal scores do not depend on images, at least in my experiments with GPT-6 Luna 0 sankalp.bearblog.dev · 21d · discuss