Seven zero-shot extraction and classification families demoed, benchmarked and cross-compared, with sizes, licences and costs in one table.
GitHubDocuments & data
Documents & data
11 builds
Frozen protocol, raw predictions, calibration and latency for Jev 1.13, PrismNLI-0.4B and Laya. Laya ties Jev on dair-ai/emotion and trails by 10–33 points elsewhere.
GitHubDocuments & data
Zero-shot benchmark: Laya's advertised win over Jev does not reproduce on four datasets
- tweet_topic
- Jev 0.793 vs Laya 0.632
- emotion
- 0.587 vs 0.587 tie
Six classifiers over SST-2, AG News and more, reporting accuracy, macro-F1, ECE, p50/p95 latency, throughput and cost side by side. Laya runs locally on MPS or CPU.
GitHubDocuments & data
jevbench: Jev vs GPT-5-mini, Claude Sonnet 5, fine-tuned DistilBERT, BART NLI and Laya
Anthony Alcaraz's talk demo routes typed decisions through Jev and shows Laya's answers beside them. On the TSMC run Laya rejected every true claim; that's the point.
GitHubDocuments & data
Agentic GraphRAG over S&P 10-Ks with Laya as a shadow decision engine beside Jev
Measures the decision head's attention drop-off on long inputs across 400 documents, then chunks, screens and aggregates, or locates the one passage that matters.
Collects vacancies, filters them against a candidate profile, ranks with the multilingual Laya checkpoint and prints IT and warehouse tables plus a Markdown report.
GitHubDocuments & data
Job search in Denmark: aggregate jobnet.dk and jobindex.dk, rank matches with Laya
Companion service that reads Lidarr's manual-import queue, scores every candidate release and track in one pass, and picks the right Single/EP/Album with calibrated probabilities.
GitHubDocuments & data
lidarr-decision-import: resolve Lidarr's stuck imports with Laya instead of an LLM
Describe a past conversation in plain language and Chat Seek finds it across local agent histories, reranks with the receptron Laya runtime, and offers a Resume action.
There’s something cute about giving a probabilistic classifier a freshman probability exam. So I gave @typesafeai Jev, SemIf, and Laya ~1000 adapted questions on probability and countability from Berkeley exams Jev: 83.7% SemIf: 61.6% Laya: 31.2% A little stress test for the
X postDocuments & data
~1,000 Berkeley probability exam questions: Jev 83.7%, SemIf 61.6%, Laya 31.2%
- Jev
- 83.7%
- SemIf
- 61.6%
- Laya
- 31.2%
I made a postgres plugin for the Laya decision models, using @Kelwing's Rust framework for running them
X postDocuments & data
pg-laya: native PostgreSQL inference for Laya decision models
I forked Needle (the Chrome extension) to use Laya instead of Jev. Fully local AI browser search. Try it out here: https://t.co/SYB7HQfya9 It is not a semantic search in strict terms, it will match your search to semantically similar results.
X postDocuments & data