Viv(@Vtrivedy10):“Inkling 2 Small was trained with RL on hundreds of thousands of long-horizon coding tasks across multiple agent harnesses and context-compaction strategies. We increased the quality of our synthetic coding data pipeline and moved beyond unit-test rewards alone; many tasks included an agentic RL grader that evaluated how the model approached the problem, not just whether its code passed.” good view into the bar that high quality needs to hit + where a lot more focus will be put on Env creation + grading

2026.11.06 03:01

“Inkling 2 Small was trained with RL on hundreds of thousands of long-horizon coding tasks across multiple agent harnesses and context-compaction strategies. We increased the quality of our synthetic coding data pipeline and moved beyond unit-test rewards alone; many tasks included an agentic RL grader that evaluated how the model approached the problem, not just whether its code passed.” good view into the bar that high quality needs to hit + where a lot more focus will be put on Env creation + grading

Thinking Machines@thinkymachines

2026.11.05 23:43

Introducing Inkling 2 Small. Scoring 31 on the AA Intelligence Index, it's a big jump over its predecessor. Inkling 2 Small is available for fine-tuning and inference on Tinker today, with full weight release planned soon.