HAhandfuloflight·Oct 1, 2026
In Clef: Open-source decision models, and new RL fine-tuning platformNandhaKishorM
laya
Python2026–2026
NandhaKishorM / laya
laya
Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.
5Distinct people
7Mentions
0Explicit recommenders
35.5KGitHub stars
What to know before exploring
What it is
Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.
GitHub
Where it is used
No documented product use has been verified yet.
What people are saying
No recommendation phrase was found in the indexed comments.
No classified warning is attached to this page. Read the discussions before treating silence as approval.
Also in these discussions
No other repository is repeatedly linked in the same discussions.
This week on Hacker News
Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 5:04:57 PM UTC.
No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.
Mentions over time
HN mentions by day7 dated mentions
Observed mentions: 2026-09-18 20:47:10 UTC to 2026-10-01 18:12:30 UTC.
Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.
View mention counts and date ranges
| Period | Start (UTC) | End (exclusive, UTC) | Mentions | Submissions | Comments |
|---|---|---|---|---|---|
| Sep 18 | 2026-09-18 00:00:00 UTC | 2026-09-19 00:00:00 UTC | 1 | 0 | 1 |
| Sep 19 | 2026-09-19 00:00:00 UTC | 2026-09-20 00:00:00 UTC | 2 | 0 | 2 |
| Sep 20 | 2026-09-20 00:00:00 UTC | 2026-09-21 00:00:00 UTC | 0 | 0 | 0 |
| Sep 21 | 2026-09-21 00:00:00 UTC | 2026-09-22 00:00:00 UTC | 0 | 0 | 0 |
| Sep 22 | 2026-09-22 00:00:00 UTC | 2026-09-23 00:00:00 UTC | 1 | 0 | 1 |
| Sep 23 | 2026-09-23 00:00:00 UTC | 2026-09-24 00:00:00 UTC | 1 | 0 | 1 |
| Sep 24 | 2026-09-24 00:00:00 UTC | 2026-09-25 00:00:00 UTC | 0 | 0 | 0 |
| Sep 25 | 2026-09-25 00:00:00 UTC | 2026-09-26 00:00:00 UTC | 0 | 0 | 0 |
| Sep 26 | 2026-09-26 00:00:00 UTC | 2026-09-27 00:00:00 UTC | 0 | 0 | 0 |
| Sep 27 | 2026-09-27 00:00:00 UTC | 2026-09-28 00:00:00 UTC | 0 | 0 | 0 |
| Sep 28 | 2026-09-28 00:00:00 UTC | 2026-09-29 00:00:00 UTC | 0 | 0 | 0 |
| Sep 29 | 2026-09-29 00:00:00 UTC | 2026-09-30 00:00:00 UTC | 0 | 0 | 0 |
| Sep 30 | 2026-09-30 00:00:00 UTC | 2026-10-01 00:00:00 UTC | 0 | 0 | 0 |
| Oct 1 | 2026-10-01 00:00:00 UTC | 2026-10-02 00:00:00 UTC | 2 | 1 | 1 |
What Hacker News says
7 sourcesLaya: Multilingual, non-autoregressive System 1 decision engine
2 points · Open discussionFor anyone who was piqued by the title but couldn't stomach the unedited LLM blogpost, you can read the similarity AI-genned docs for Laya directly: https://github.com/NandhaKishorM/laya
In Does an open-weight decision model beat a hosted one? Jev vs. LayaWhy wouldn't i use something like these?
- https://github.com/NandhaKishorM/laya
- https://github.com/deepanwadhwa/OpenDecision
In OpenAI is well positioned to fast-follow JevAnd how is laya previous art? The project was vibecoded and posted yesterday.
https://github.com/NandhaKishorM/laya/commits/main/
https://huggingface.co/convaiinnovations/laya/commits/main
In I built non-autoregressive decision models with RL a year agoToday, he released Laya, a model based on his paper: https://github.com/NandhaKishorM/laya
In OpenJev