#rate-limits

[ follow ]
#model-performance #hardware-compatibility #time-to-first-token #interactive-applications #openai #codex
JavaScript
fromInfoWorld
4 days ago

27 questions to ask when choosing an LLM

Model performance is crucial for hardware compatibility, speed, and rate limits in real-time applications.
Software development
fromArs Technica
2 months ago

OpenAI picks up pace against Claude Code with new Codex desktop app

OpenAI released a macOS Codex desktop app to manage multiple coding agents, add Skills and Automations, and doubled Codex rate limits across paid plans.
fromGSMArena.com
4 months ago

OpenAI starts rolling out group chats for ChatGPT users globally

OpenAI began piloting group chats for ChatGPT users last week. The feature was available on web and mobile for logged-in users on ChatGPT's Free, Go, Plus, and Pro plans, but only in Japan, Taiwan, New Zealand, and South Korea. OpenAI said the rollout would be expanded to more regions based on feedback, which has been positive, and the company announced the rollout of group chats for ChatGPT users globally.
Mobile UX
[ Load more ]