Model Releases

The new DeepSeek-V4, like DeepSeek-V3, uses concepts from our 2024 paper on Self-Rewarding LMs -- see screenshots of their tech reports! (Co…

The new DeepSeek-V4, like DeepSeek-V3, uses concepts from our 2024 paper on Self-Rewarding LMs -- see screenshots of their tech reports! (Congrats!) Classical :) Self-Rewarding LMs from Jan 2024: http

DGX agentx-post
model-releasesjeremy-howard--x

The new DeepSeek-V4, like DeepSeek-V3, uses concepts from our 2024 paper on Self-Rewarding LMs -- see screenshots of their tech reports! (Congrats!) Classical :) Self-Rewarding LMs from Jan 2024: https://arxiv.org/abs/2401.10020

Source: Jeremy Howard (X) | 2026-04-29

Loading related sources…