Fetching from the wire…
01
02
03
04
05
06
07
08
Public story · 2026-03-08 · source-backed
Fully open model using 3:1 DeltaNet-to-attention that matches Olmo 3 with 49% fewer tokens. Novel theoretical proof that hybrids are strictly more powerful than either transformers or RNNs alone. Trained on 512 GPUs. Full weights, checkpoints, and code released. AI2 Blog
Each link below shares sources, entities, or timing with this story.
Shared entities / Same source / Shared topic / Earlier coverage
Both cover AI2 Blog, OLMo, RNNs; cite the same source (AI2 Blog); overlapping topics (alone, architecture, hybrid, model, olmo).
Shared entities / Shared topic / What happened next / Tension
Both cover Full, GPUs; overlapping topics (code, gpus, model); picks up the Full thread on 2026-05-09.
Shared entity: DeltaNet / Same source / Shared topic / Tension
Both cover DeltaNet; cite the same source (AI2 Blog); overlapping topics (code, hybrid).
Shared entities / Shared topic / What happened next
Both cover Full, Trained; overlapping topics (code, full, model); picks up the Full thread on 2026-07-21.
Shared entities / What happened next / Tension
Both cover Full, Fully; picks up the Full thread on 2026-07-23; pushes against this story (against).
Shared entity: GPUs / Shared topic / What happened next / Tension
Both cover GPUs; overlapping topics (code, gpus); picks up the GPUs thread on 2026-08-11.
Shared entity: Full / Shared topic / What happened next / Tension
Both cover Full; overlapping topics (code, full); picks up the Full thread on 2026-07-28.
Both cover Full; overlapping topics (architecture, code); picks up the Full thread on 2026-06-01.