Traits of next generation reasoning models
Автор: Nathan Lambert
Загружено: 2025-06-05
Просмотров: 6451
Описание:
Current AI models are extremely skilled, which was seen as the step change in evaluation scores across the industry in the first half of 2025, but often fail when presented with even medium time-horizon tasks. This talk presents a taxonomy of 4 traits of reasoning models -- skills, calibration, strategy, and abstraction -- that will be crucial to creating the next generation of AI applications. With this, we focus on the latter two, strategy and abstraction, and discuss how these traits will enable long-horizon and reliable agents. The talk concludes with a scenario where these agentic behaviors are the foundation for RL continuing to scale in the coming years and post-training techniques reaching compute parity with pretraining methods sooner than later.
00:00 Everybody has reasoning models
03:18 Autonomy and the need for planning
04:53 Traits of reasoners
15:23 RL as the focus of LM development
Slides: https://docs.google.com/presentation/...
Written version: https://www.interconnects.ai/p/next-g...
Повторяем попытку...
Доступные форматы для скачивания:
Скачать видео
-
Информация по загрузке:
![The Misconception that Almost Stopped AI [How Models Learn Part 1]](https://imager.clipsaver.ru/NrO20Jb-hy0/max.jpg)
