Haider.(@haider1):million-token context window is great but what happens when an AI agent needs to remember something from three months ago? i think this is where graphon-based memory takes a different approach, connecting information across documents, conversations, images and videos rather than relying on vector search alone

2026.11.11 05:41

million-token context window is great but what happens when an AI agent needs to remember something from three months ago? i think this is where graphon-based memory takes a different approach, connecting information across documents, conversations, images and videos rather than relying on vector search alone

Arbaaz Khan@graphonfounder

2026.11.10 17:05

After years working on robot memory at @NASAJPL, @GoogleDeepMind , @Meta and @nvidia, @clarkzhango and I kept asking: why does AI still forget? Today, with @deepakmishraVC, we’re announcing @GraphonAI and our $35M Series A just 6 months after our seed. • #1# on ATM-Bench, ATM-Bench Hard • 94% on LoCoMo • 84% on DolphinBench, 10x cheaper • A new cost-accuracy frontier across 7 benchmarks

轉發到社區