Inkling's continuous thinking effort trades cost against performance
Original titleCost and latency are important in real-world use cases. Inkling's continuous thinking effort lets you pick your point on the cost/perform...
AISummary
Thinking Machines says its Inkling model offers continuous thinking effort, letting users choose their point on the cost-performance curve. The company claims it can reach the same benchmark score using a fraction of the tokens.
Source: Thinking Machines · x.comPublished · added here