AIWHYS

Technology

in-context learning

2 synchronized stories carry this tag.

Open & specialistPreview

BigQuery exposes TabFM zero-shot prediction through SQL

Google added TabFM to BigQuery in preview. Users can run zero-shot regression or classification on structured tables with AI.PREDICT and evaluate results with AI.EVALUATE, without fitting a task-specific model or tuning hyperparameters.

Why it matters: The June research model is now a managed data-warehouse function. That lowers the setup cost for baselines on churn, fraud, operations and other tabular tasks while making SQL permissions, data boundaries and evaluation design part of model use.

Read storyOriginal source · docs.cloud.google.com
Agents & toolsPreprint

ContinualSkillBench separates reusable skills from temporary context adaptation

Across five domains with 100 connected tasks each, sequential experience improved results, but explicit skill libraries performed comparably to retaining prior context on average.

Why it matters: A growing skill folder can look like durable learning while most gains actually depend on the training conversation still being present.

Read storyOriginal source · arxiv.org