Inkling-Small began training after its larger counterpart, so it benefits from everything we learned: an improved pre-training data mix, a refined ML recipe, on-policy distillation with Inkling as the teacher, and two further weeks of agentic coding RL.
Thinking Machines' Inkling-Small Gains From Lessons of Larger Inkling
AISummary
Thinking Machines says Inkling-Small began training after its larger counterpart and benefits from the lessons learned. The post cites an improved pre-training data mix, a refined ML recipe, on-policy distillation using Inkling as the teacher, and two additional weeks of agentic coding RL.
Post on XView on X
Source: Thinking Machines · x.comPublished · added here