OpenAI

Chinchilla's lesson: how did it reshape architecture and training choices after 2022?

Pair each transformer family with its canonical pretraining objective

Spend a fixed parameter budget: more layers or wider d_model, and what does the evidence say?

Why did decoder-only architectures take over tasks T5-style encoder-decoders used to win?

Two providers both advertise $0.50 per million output tokens, why is that comparison still dishonest?

When does inflating the system prompt actually lower cost per call?

Diagnose the reasoning error in 'a bigger tokenizer vocabulary always cuts our token bill'

'Prompt caching cuts our bill by 90 percent across the board', what's overclaimed?

A teammate randomized system prompts per user and expects the prompt cache to still help, what's wrong?

Predict the break-even read count for Anthropic prompt caching given the 1.25x / 0.1x rates