#subq — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #subq, aggregated by home.social.
-
SubQ: First Sub-Quadratic LLM with 12M-Token Context (2026)
On May 5, 2026, Miami startup Subquadratic launched SubQ — the first frontier LLM built on sub-quadratic sparse attention — with a 12-million-token context window an...
https://wowhow.cloud/blogs/subq-subquadratic-12m-token-llm-developer-guide-2026
-
I always maintained that current #Ai
is just the early tech, that we will get better at building better models with better algorithmshttps://thenextweb.com/news/subquadratic-subq-sparse-attention-llm-bottleneck
-
Subquadratic – Introducing SubQ 1.1 Small
https://subq.ai/subq-1-1-small-technical-report
#HackerNews #Subquadratic #SubQ #Small #Update #TechNews #AI
-
LLM ARCHITECTURE SEES RAPID SHIFT
SubQ LLM's new Subquadratic Sparse Attention (SSA) works faster for long texts. It helps AI handle more information and could change how AI is used.
-
A new AI model called SubQ uses a faster way to process long texts, making it much more efficient than older models. This could lead to AI that understands more.
#LLM #AI #SubQ #Transformer #ArtificialIntelligence
https://newsletter.tf/new-llm-faster-attention-changes-ai/ -
A Miami-based startup called Subquadratic came out of stealth last week with a single claim that’s either the most important architectural shift since the 2017 transformer paper or the most sophisticated AI hype in recent memory. They say they’ve built the first LLM that doesn’t rely on quadratic attention and that this lets them run a 12 million token context window at roughly one-fifth the cost of frontier models.
https://firethering.com/subq-12m-token-context-llm-subquadratic-attention/