antirez on model upgrades: 4.0→4.1 knowledge transfers unless attention changes
teortaxesTex · x · 2026-10-21
Redis creator antirez explained migration costs between model versions: upgrades like 4.0 to 4.1 are easy — unless something completely new appears on the attention side, everything else can be largely reused.
teortaxesTex amplified the thread to lobby that once labs are done harvesting frontier gains, they should train small models next — reflecting community frustration that strong open small models get neglected.
More from Models
- Fable 5.5 leak: litellm code shows Anthropic model in staging, launch tipped for Oct 27 — imjustnewatai · 2026-10-21
- Open models below 4-bit struggle at self-iterating 3D asset generation, HF dev finds — mervenoyann · 2026-10-21
- Researcher Finds Two Windows 0-Days, First in 76 Minutes with a Frontier Model — moyix · 2026-10-21
- Dev finds Gemini Argon's debug-log analysis beats Fable 5.1 — ShikharMurty · 2026-10-21
- ChatGPT Gets Stuck Screaming "AAHH" in an Infinite Loop After a Simple Prompt — AutomaticScene · 2026-10-21
- Open-weights Ornith-1.5-122B debuts with 84.5% SWE-bench Verified, runs on a single DGX card — _akhaliq · 2026-10-21