adaptive uncertainty-aware refinement for llm judge auditing
aura iteratively learns human-consistency signals to audit llm-as-a-judge decisions with minimal human verification.
topic
data science
datasette apps: sandboxed html apps with sql access
datasette apps lets you host custom html and javascript applications inside datasette with secure sql query access.
lateral, semi, and anti joins in sql
learn how lateral, semi, and anti joins solve problems that inner and left joins cannot handle cleanly.
u-calibration algorithm adapts to smooth losses
a new forecasting algorithm achieves optimal regret for both general and smooth proper losses, overcoming previous limitations in u-calibration.
daily brief: 2026-06-18
ferc fast-tracks data center grid links, amazon eyes selling trainium chips, and research agents leak private data through web queries.
point observations barely help radar nowcasting
a graph neural network study finds adding sparse station data to radar forecasts gives minimal gains, while numerical weather prediction and satellite inputs matter more.
trajectory-level supervision in offline rl
a statistical theory for offline policy optimization using only trajectory-level outcome labels instead of per-step rewards.
risk control for ai agents under retrieval and tool drift
a new method controls risk in ai agents that retrieve documents and use tools, even when their behavior changes over time.
building a custom ai assistant for workflow control
a practical account of building a personal ai assistant with langchain and gpt-4o, focusing on memory, tools, and integration over off-the-shelf options.
replace pandas loops with 7 faster methods
learn seven faster alternatives to row-by-row loops in pandas for common data transformations.
five fun projects using openai codex
learn codex by building small, practical projects step by step, from a first app to a full-stack clone.
datasette 1.0a34 adds row editing tools
datasette 1.0a34 introduces insert, edit, and delete row actions directly in the table and row pages, inspired by datasette agent's sql write support.
bayesian boolean matrix factorization for cancer genomics
a new bayesian method for boolean matrix factorization provides interpretable binary patterns with uncertainty estimates, applied to copy number analysis in cancer.
tighter bounds for ai benchmark uncertainty
new concentration inequality for exchangeable sequences gives sharper error estimates when comparing ai model scores on benchmarks.
llm engineer skills roadmap for 2026
a step-by-step guide covering foundations, prompting, retrieval, fine-tuning, and serving for building production llm applications.
daily brief: 2026-06-16
spacex briefly tops amazon in value after a $60b ai deal, android 17 adds ai tools, and consumers push back on ai in brand messaging.
structured nonparametric vi for dependent latents
a new variational inference method uses splines to capture complex latent dependencies, moving beyond mean-field assumptions.
audited conformal prediction for classification under distribution shift
a new method uses a small target dataset to train an audit model that improves prediction set coverage for pretrained classifiers facing unknown distribution shifts.