Lead story
Ask your AI
Top stories
Models & availability
Latest
Lead story
Ask your AI
Top stories
Models & availability
Latest
Amp announced speed improvements in its deep and rush modes, with first token arrival 87% faster and entire responses 32% faster at p50, and up to 40% end-to-end speedup on long-horizon tasks, attributed to using websockets for OpenAI communication and a recent rebuild.
From the source
The first token now arrives 87% faster and entire responses are 32% faster, p50, in Amp's deep and rush modes.
ampcode.com