Together AI is announcing a new model called M3, which features sparse attention and a 1 million token context window. The announcement is scheduled for tomorrow and will be a live event, with MiniMax AI also participating. This event aims to provide insights into the model's architecture and capabilities. AI
IMPACT This release could push the boundaries of context window length and attention mechanisms, potentially influencing future model development.
RANK_REASON New model release announcement from an AI lab. [lever_c_demoted from frontier_release: ic=2 ai=1.0]
Read on X — Together (inference / OSS) →
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →