HomeAI · summaries
Storia in 2 fonti
Agents-A1 achieves 1T-model performance through long-task training, not bigger parameters
Shanghai AI Laboratory's Agents-A1, a 35B-parameter model, matches trillion-scale rivals through extended trajectory training and multi-teacher
Confronto fonti
2 prospettive sulla stessa storiaTimeline cronologica
- ·
cryptobriefing.com
Agents-A1 achieves 1T-model performance through long-task training, not bigger parameters
Shanghai AI Laboratory's Agents-A1, a 35B-parameter model, matches trillion-scale rivals through extended trajectory training and multi-teacher
- ·
dev.to
A 35-billion-parameter agent that punches like a trillion-parameter model
Shanghai AI Lab argues you can reach giant-model performance on long tasks not by adding parameters, but by training on much longer chains of real work.