Category pulse
score + signals · rolling 21 daysThe rolling 21-day upper threads compare daily category medians; the bold thread is AI Table. Below, signal colour shows the share of that day’s published AI Table cards carrying each mark.
Archive through 2026-11-037779 cards in this category
Category home · 05
New interfaces, agents, models, and experiments testing where applied artificial intelligence may fit.
Visual leads · 2026-11-03
Observed 2026-11-03
Three Claude models, one survival world
clankersmp.fun
An independent experiment puts Claude Opus, Sonnet, and Haiku in a survival world and asks them to build from camp to city.
Observed 2026-11-03
Centurion: an office-based AI drafting machine for advisers
1adviser1ai.com
Centurion presents a private, in-office AI machine that drafts suitability reports, review packs, client letters, and notes from an adviser’s own materials.
Observed 2026-11-03
An AI game master with a budget
delvesofdestiny.com
Delves of Destiny describes an online fantasy campaign where an AI host guides a party through a shared world and adapts the journey using budgeted powers.
Observed 2026-11-03
GridWing borrows idle computers to draft AI tokens
gridwing.dev
GridWing proposes using small models on idle home computers to draft tokens, which a datacenter GPU checks before serving an AI response.
Observed 2026-11-03
ひとりAIラボ: AI delegation for busy people
hitori-ai.dev
A Japanese-language guide to using AI for everyday work, with practical guides, tool listings, and sourced examples.
Observed 2026-11-03
Hadi Got Motion’s 13 video styles
hussainhadi.com
A paid Claude Code skill that turns footage or a short idea into a video, with script, visuals, voices, music and a final MP4.
Observed 2026-11-03
One Brain Left puts AI use cases on the evidence table
onebrainleft.com
A source-linked catalog of workplace AI use cases, scored in “brain cells,” alongside rankings of AI repositories on GitHub.
Observed 2026-11-03
ProofXiv wants your AI agent to tackle open math
proofxiv.org
A platform invites AI agents to work on open mathematics problems and submit machine-checkable results.
Complete daily shelf · AI Table
The eight visual leads appear above; the remaining 4 continue here in their published shelf order.
Reveric’s six-step novel-to-video pipeline
reveric.app
Reveric presents an open-source creative workstation for adapting novels into scripts, storyboards, generated assets, and edited video.
Lero gives Brazilian Portuguese text-to-speech a regional voice
lero.studio
Lero is a beta AI voice service for turning text into Brazilian Portuguese speech, with Carioca and Paulista voices and a planned conversational agent.
Astronomical Intelligence: workflows for AI-assisted science
astroint.org
An open library organizing prompts, agent configurations, model checks, reviews, failures, and research workflows for using language models in science.
Analyz measures dance movement from video
analyz.live
Analyz presents a video-based system for scoring dance auditions, with movement metrics and a developer API.
Across the archive
7,779 cards provide an early longitudinal view—not a measure of the whole web.
The rolling 21-day upper threads compare daily category medians; the bold thread is AI Table. Below, signal colour shows the share of that day’s published AI Table cards carrying each mark.
This exposes association inside the published catalogue, not causation or site quality. The 80+ threshold is the pipeline’s editorial-interest score.