News for hackers. Stuff that matters.

rosmine

Show HN: Deft Writing, an AI lab for non-slop LLMs

https://deftwriting.com

Announcing Deft, a new AI lab for better writingCurrently, 86% of user queries are fully human according to pangram.This is still a small beta model and it might make mistakes. We are launching our public beta now to get more feedback before scaling up.Tips for better performance: - Add more details to your prompt. If you just provide a short sentence prompt, it will likely get detected as...

( Read More... | no comments | 2 points | on HN )
Re:Was my $48K GPU server worth it? on Thursday May 21, 2026 @09:38PM (#48230954)
My first advice is to have a test set with clear improvement, and a clear "wow" demo use case. There are lots of "breakthroughs" that seem good but aren't (e.g. some new architecture that doesn't mask past tokens correctly and leaks information), so people will assume it is wrong. To prevent this, you need to be extremely rigorous in your launch materials. If you can make it into a product that people can try out themselves, that goes a long way. You don't need to open source any code (I haven't yet) if people can try it out some other way like a demo website. Good luck! Ping me if you want to chat more
Re:Was my $48K GPU server worth it? on Thursday May 21, 2026 @04:35PM (#48228543)
I agree :) Also, I heard Teknium trained the original Hermes model on 2x 4090. You can do a lot with a little compute
Re:Was my $48K GPU server worth it? on Thursday May 21, 2026 @04:31PM (#48228499)
Yes! It scared me too. I tried to insure it under my renter's insurance policy, but they not surprisingly refused. I had to get business insurance to cover it
Re:Was my $48K GPU server worth it? on Thursday May 21, 2026 @04:28PM (#48228465)
Hi! Thank you so much for posting this! I got back luck/timing when I tried, so happy it made it to the front page! (I am the author)

Show HN: An LLM that's better at writing

https://dft.rosmine.ai/

Standard LLM training is surprisingly bad at making the model outputs match the training data distribution, so the writing quality is bad.I made a new training algorithm called Distribution Fine Tuning (DFT) to fix this.The demo lets you try out a model trained with DFT.More details in the technical report: https://rosmine.ai/2026/05/18/fixing-llm-writing-with-distri...

( Read More... | no comments | on HN )