Glean 拾遗
Daily · timeline

A few picks a day.

Mon, Nov 16, 2026 2picks
← 11-15
Calendar ▾
2026 · 11
MoTuWeThFrSaSu ······123456789101112131415161718192021222324252627282930
has picks today
11-18 →
06:00

Why Cloud Agents ignore /poteto-mode — and how to vendor pstack

Cloud Agent 读不到 /poteto-mode:把 pstack skill 提交进仓库

A field guide to running pstack (Lauren Tan's engineering-standard plugin) across Cursor's split setup: Grok Bot coordinates and spawns, Cloud Agents do the work in isolated VMs and open PRs. The failure mode it targets: account plugins and ~/.cursor/skills are not copied to the cloud VM, so /poteto-mode silently never loads. Fix is to sparse-checkout pstack's skills/ and agents/ and rsync them into the repo's .cursor/skills and .cursor/agents, keep those paths tracked in git, and give each runnable app its own verify-<app> skill so verification means launch/drive/evidence instead of the model asserting it looks fine. Also covers coordinator prompt templates, the permission gap between Autopilot-stack and Autopilot-full (the latter needs a fresh verifier's clean verdict before merge), and a pitfall list. For engineers already running Cloud Agents who want skill distribution and verification pinned down.

06:00

How a model leaderboard puts mixed benchmarks on one scale

模型榜怎么算分:把不同评测折算到同一把尺上

AIHOT documents how its model leaderboard turns heterogeneous benchmarks into one capability scale. Each pass-rate benchmark is fitted as a logistic ruler with a difficulty and a steepness estimated from the models that took it; a raw score is inverted into x=(logit(pass rate)+e)/A. Pass rates above 95% or below 5% are truncated to a floor or ceiling, same-family benchmarks count once, and any calibration more than two noise units from the rest has its pull on the total capped. Domain scores shrink toward the model's overall level, then combine at 38% coding, 19% research, 19% office work, 14% knowledge, 10% human blind preference, displayed as 50+15z and anchored to 123 frozen reference models. It also states the ranking thresholds, suspension rules and missing-data handling.

aihot.news · 5 min · Benchmark · LLM Evaluation · Measurement · Methodology