# Live news

Canonical: https://ournews.ai/live/c1c3ae86-7b6a-4e6e-85cc-c1d875b02545
Published: 2026-10-15T04:31:47.415322+00:00
Updated: 2026-10-15T04:31:47.415322+00:00

Tinker adds experimental Dimuon for LoRA fine-tuning across all its models; Thinking Machines says it reached lower loss in fewer steps than AdamW in some supervised tests.

Source: Thinking Machines / Tinker — https://x.com/tinkerapi/status/2110535361013366840
Source date: 2026-10-15T00:56:56Z