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.
Set DEMO_DECISION_ENGINE=laya to let Laya act instead of shadow.
README not available at build time.
Seven zero-shot extraction and classification families demoed, benchmarked and cross-compared, with sizes, licences and costs in one table.
@umstek · Documents & data · free for the local rows
@umstek
GitHub
Documents & data
free for the local rows
-
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.
@elcronos · Documents & data
@elcronos
GitHub
Documents & data
-
-
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.
@dhruvmehra · Documents & data · $0 for the local rows
@dhruvmehra
GitHub
Documents & data
$0 for the local rows
-
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.
@myxamediyar · Documents & data · free, no extra cost over a larger context window
@myxamediyar
GitHub
Documents & data
free, no extra cost over a larger context window
-