PulseAugur
EN
LIVE 21:28:29

New System One decision model shows rapid learning on MacBook

By PulseAugur Editorial · [1 sources] ·

A new decision model called System One, developed by the author of Laya and VegaML, has been tested on a MacBook. This model utilizes a frozen Qwen3.5-0.8B model and a 14M-parameter "physics engine" to determine answers by outputting probabilities rather than generating text. Initial tests showed a 51% topic accuracy in zero-shot mode, which improved to 65% after fitting with 40 labeled prompts, demonstrating a quick learning capability from a small dataset. AI

IMPACT Demonstrates potential for efficient, on-device AI model learning with limited labeled data.

RANK_REASON The cluster describes a new model release and its performance on benchmarks, fitting the research category. [lever_c_demoted from research: ic=1 ai=1.0]

Read on Mastodon — fosstodon.org →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

New System One decision model shows rapid learning on MacBook

How we ranked this

Signal score
11 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The cluster describes a new model release and its performance on benchmarks, fitting the research category. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. Mastodon — fosstodon.org TIER_1 English(EN) · [email protected] ·

    New "System One" decision model from the author of Laya: VegaML. Into the benchmark it went, on my M4 16 GB MacBook. How it works: a frozen Qwen3.5-0.8B reads t

    New "System One" decision model from the author of Laya: VegaML. Into the benchmark it went, on my M4 16 GB MacBook. How it works: a frozen Qwen3.5-0.8B reads the question, then a 14M-parameter "physics engine" lets a ball roll into the valley of the right answer. No text is gene…

    LINKS blog.mornati.net/laya-0-4-2-and-vegaml-a-…

RELATED ENTITIES

RELATED TOPICS