(medium.com)

68 points peakji | 1 comments | 22 Oct 24 16:07 UTC | HN request time: 0.199s | source

Steiner is a series of reasoning models trained on synthetic data using reinforcement learning. These models can explore multiple reasoning paths in an autoregressive manner during inference and autonomously verify or backtrack when necessary, enabling a linear traversal of the implicit search tree.

Blog: https://medium.com/@peakji/a-small-step-towards-reproducing-...

Hugging Face: https://huggingface.co/collections/peakji/steiner-preview-67...

Show context

swyx ◴[22 Oct 24 18:34 UTC] No.41917274[source]▶

>>41915735 (OP) #

advice to OP - you hurt your own credibility posting on medium dot com. just blog on huggingface or substack or hashnode.

replies(3): >>41917456 #>>41918832 #>>41921519 #

peakji ◴[22 Oct 24 18:55 UTC] No.41917456[source]▶

>>41917274 #

I'm new here. Just curious, why avoid Medium? Is it a Hacker News thing, or did I miss something?

replies(3): >>41918051 #>>41918091 #>>41918187 #

1. swyx ◴[22 Oct 24 20:11 UTC] No.41918187[source]▶

>>41917456 #

its just a "tell" that you dont mind the poor reader experience and being associated with the rest of low quality slop that is on medium. many of us here have simply given up clicking on anything medium related

↑

Show HN: Steiner – An open-source reasoning model inspired by OpenAI o1