Cover image

Rewind Before the Uncertainty Peak

REWIND improves language-model reasoning by revising earlier uncertainty transitions, but its accuracy gains must be weighed against additional computation and unsuccessful repairs.

November 12, 2026 · 8 min · Zelina
Cover image

Same Request, Different Batch, Different Bits

How BIEvolve adds batch-invariance checks to AI-generated GPU kernels, improving numerical consistency while retaining most benchmark speedup.

November 12, 2026 · 7 min · Zelina
Cover image

The Score That Shapes the Forecast

WAC shows how consequence evaluation can improve action selection by shaping the predictive representations a planner learns, while exposing the limits of benchmark scores and counterfactual supervision.

November 12, 2026 · 8 min · Zelina
Cover image

The Summary Kept the Files. The Agent Lost the Fix.

Compact-Bench shows why preserving technical details during context compaction does not guarantee that a coding agent can finish its work.

November 12, 2026 · 9 min · Zelina
Cover image

When Better Calibration Means Worse Confidence Ranking

A confidence score can look well calibrated yet struggle to identify unreliable LLM answers, changing how teams should evaluate automated routing.

November 12, 2026 · 10 min · Zelina
Cover image

A Different Forecast Without a Different Model

Shared low-rank adaptations improve customer-level electricity forecasts, but the reported efficiency gains still require operational verification.

November 11, 2026 · 8 min · Zelina
Cover image

A Reliable Alarm Can Still Miss the Drift

Why statistically valid runtime monitoring can miss changes in stochastic controllers, and how spatial evidence improves detection without guaranteeing it.

November 11, 2026 · 9 min · Zelina
Cover image

Fewer Successful Attacks, Worse Audit Safety

Why an AI agent's memory of a caught attack can reduce subsequent sabotage without necessarily improving the safety of its monitoring system.

November 11, 2026 · 9 min · Zelina
Cover image

More Tokens Per Step, More Work Per Answer

Why accepting more draft tokens can increase LLM inference work, and how to evaluate decoding speedups without overlooking longer responses or accuracy losses.

November 11, 2026 · 7 min · Zelina
Cover image

Remembering Why Is Not Proving Why

CauProphet explores whether agents make better decisions by retaining and revising causal hypotheses, and what its benchmark gains reveal about the costs and limits of explanatory memory.

November 11, 2026 · 9 min · Zelina