New ask Hacker News story: Open-sourced jev architecture last year with model,paper and dataset
Open-sourced jev architecture last year with model,paper and dataset 4 by nandakishor_ml | 2 comments on Hacker News. Everyone now talks about the architecture that's not auto regressive and does lightning fast probability prediction with a json schema. I worked on this literally one year back in March 2025, published an arxiv paper, pushed the model to huggingface along with the pypi package and training dataset. And then one year later, a frontier lab came, proposing the same idea like literal breakthrough without technical papers, open weights and no open dataset. For anyones information the main guiding model is RL not embedding model or LLM Paper: https://ift.tt/lXkYSAf Model: https://ift.tt/HRIlLf4 Dataset: https://ift.tt/qAS2MER Also the second work published in September 2025 was exactly the same one jev proposed now Paper: https://ift.tt/OkPpMF6 My model uses PPO over sequence embeddings to output turn-by-turn conversion trajectories (probabilities from 0.0 to 1.0). ...