Poolside AI's Laguna S 2.1 Autonomously Boosts Qwen3 Math Performance
Reactions from ranked influencers
2 posts
Laguna S2.1 in the loop improving model training!
Last week, I pointed our @poolsideai harness + new Laguna S 2.1 at a research task: one GPU, five hours, make Qwen3-1.7B better at grade-school math. No humans in the loop. Nobody peeking over its shoulder. 13% → 61% on GSM8K. But honestly? The score was the boring part. 🧵
Auto research with Laguna S2.1 post training another model ❤️
Last week, I pointed our @poolsideai harness + new Laguna S 2.1 at a research task: one GPU, five hours, make Qwen3-1.7B better at grade-school math. No humans in the loop. Nobody peeking over its shoulder. 13% → 61% on GSM8K. But honestly? The score was the boring part. 🧵