Skip to main content
⚙ Methodology How the signal gets made v1.2 · 2026-07

How we score the signal.

Where the data comes from, how the local analysis model and LLMgram URL Reader enrich it, what the numbers mean, and why you can (and can't) trust this page. No black boxes.

LLMgram is a curation layer. It doesn't produce news — it ingests public AI content from roughly 100+ primary configured sources (with an optional expansion pack), enriches weak excerpts with the dedicated LLMgram URL Reader, runs structured analysis, and ranks by source trust, evidence, recency, and usefulness. Everything on this page explains exactly how that happens, because if you can't see how a score is made you shouldn't trust it.

Data sources

Every public surface on llmgram pulls from a named upstream. Ranking is not “we picked what we like” — items arrive from feeds, APIs, curated registries, or scheduled scrapers. A few surfaces (Hardware Red Room today) are still curated seed graphs and are labeled as such.

SurfaceUpstreamMethodCadence
AI Signal~105 primary RSS/scrape/X sources in fetch-rss.py (+ optional expansion pack)Fetch + LLMgram URL Reader enrichment + local/Grok structured analysisOps cron (freshness target ≤6 h)
Use CasesHand-curated evidence registryHuman review against a public repo, documentation, demo, or reproducible workflowOn verified editorial update
WeeklyAI Signal snapshotEditorial Top 10 digest from scored articlesBuilt with AI Signal critical sync
Git SignalCurated GitHub repo list / API snapshotRepo metadata + README + analysisOps sync script
AI Papersai-papers-data.json research graphScored/grouped paper index for the AI Papers surfaceOn dataset sync
Skills SignalExternal skills snapshot → skills-signal-data.jsonSync + publishOps sync script
Compute MapEpoch AI — AI Data Centers datasetCompacted static JSON for the globe UIOn refresh script run
Hardware Red RoomCurated seed graph (AI Signal candidates planned)Conservative source-backed seed MVPOn curated update
LLM ArchitecturesSebastian Raschka LLM Architecture GalleryGallery scrape/builder + attributionSuggested every 6 h
Company RadarsLabs registry + public profiles / evidence queueRadar pipeline + roster verificationRotation / varies by lab
AI MercatoLabs registry + roster-backed affiliationsVerified people/movements graphOn rebuild
WikiAI Signal-derived entity graphSeed/enrich from signal (full sync)Scheduled full sync
AcademyTutorial-like items filtered from AI SignalRegex prefilter + optional Grok verificationWith Academy builder / signal

What "structured analysis" means

AI Signal uses a local analysis model by default, with Grok as fallback/legacy path when explicitly configured. Before analysis, weak or title-only inputs are enriched through llmgram-url-reader, the LLMgram-owned fork/adapter for URL extraction. Celeste URL Reader can inform the implementation, but the production contract is LLMgram's own POST /summarize service.

How the signal score is prompted

The analysis prompt asks for a score based on a weighted mix of novelty (is this new information, or the Nth write-up of the same thing?), importance (does this change how practitioners work?), rigor (is there evidence, or is it hype?), and freshness (when was this published?). The weekly digest adds an extra editorial filter: unverified X leaks and speculative frontier-model rumors can remain searchable in AI Signal, but they are not allowed to dominate the canonical weekly issue.

What a score means in practice:
0.85 + Rare. Genuinely important — models launches, breakthrough papers, major framework releases. These are the items you'd regret missing.

0.50 – 0.84 Useful context. Good reads, but skippable if you're pressed for time.

Below 0.50 Noise. Kept in the corpus for search, hidden from default views.

Limitations you should know

Grok is a language model. That means the scoring is opinionated and inconsistent across runs. We mitigate but don't eliminate this:

Refresh cadence

Different surfaces refresh at different rates. Exact crontab lines live on the ops host; the contracts below match the scripts and health checks in this repo.

Use Cases evidence gate

Use Cases turns selected capabilities into evergreen workflows. AI Signal and other sources may surface candidates, but no model can publish a case automatically. A public case requires a concrete outcome, explicit inputs and steps, at least one reachable evidence link, and a dated editorial verification.

What we don't do

Provenance & source code

LLMgram is built and operated at llmgram.app as a public lab notebook. Pipelines, HTML, and data are in private repos for now. Every content item links back to its original source — nothing is published without attribution.

If you find a miscategorized item, a stale score, or a bug in the scoring, ping @iamsupersocks on X/Twitter or @llmgram.

Changelog