Skip to main content

Posts

Featured

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). ...

Latest Posts

New ask Hacker News story: Can I get insurance for company renting humanoids for parties?

New ask Hacker News story: Zuck's bot increased our Vercel bill 10x

New ask Hacker News story: Tell HN: An inside view of Montana's new biotech law

New ask Hacker News story: A mnemonic-free wallet where the private key never leaves the phone's TEE

New ask Hacker News story: Ask HN: Slow OpenAI Inference on AWS Bedrock

New ask Hacker News story: Day 13. Three production applications on AWS down

New ask Hacker News story: Started Learning Pentesting

New ask Hacker News story: YouTube has banned Dmitry "Savromat" Chernyshevsky

New ask Hacker News story: Tell HN: iOS 27 does not allow Apple Intelligence to be disabled

New ask Hacker News story: Ask HN: In The Matrix, the bad guys are the 'agents'. Coincidence? Clairvoyance?