LLMgram is a curation layer. It doesn't produce news — it ingests public AI content from roughly 150 configured sources, 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 surface on llmgram pulls from a specific, named upstream. Nothing is manually curated in the sense of "we picked what we like" — everything comes from a feed, an API, or a scraper that runs on a fixed schedule.
| Surface | Upstream | Method | Cadence |
|---|---|---|---|
| AI Signal | ~149 configured RSS/scrape/X sources (labs, blogs, infra, policy, research) | Fetch + LLMgram URL Reader enrichment + local/Grok structured analysis | Every 2 h + backlog jobs |
| Git Signal | GitHub API (curated repo list) | Repo metadata + README + Grok | Every 2 h |
| AI Papers | OpenAlex + SSRN | API query on tracked authors + Grok | Every 2 h |
| LLM Architectures | Sebastian Raschka gallery + handwritten notes | Manual + checker cron | Weekly |
| Hermes Live | @Teknium Twitter + GitHub PR watch | Scrape + digest | Hourly |
| Claude Code Live | Top CC voices Twitter | Scrape + digest | Hourly |
| Company Radars | Per-lab Twitter + public profiles | Scrape per lab | Varies |
| Academy | Hao Hoang — Top 50 LLM Interview Questions | Static, with permission | On update |
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.
- Category — one of ~20 buckets (model release, paper, framework, infra, agent, safety, etc.). Lets users filter.
- Themes — up to 5 free-form keywords capturing what the item is about. Drives the search index.
- Audience — researcher / practitioner / both. Not every paper matters to every reader.
- Editorial analysis — signal, summary, context, critique, key takeaway, impact score, novelty, and warnings where extraction is partial.
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.
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:
- The prompt is fixed and versioned. Changes are rare and noted in the changelog.
- Scores are rounded to 2 decimals to discourage false precision.
- Every item links to its raw source. If Grok miscategorized something, you can see the original in one click.
- Sampling bias exists. English-first sources dominate the feed. Labs outside the US/EU/China are underrepresented.
Refresh cadence
Different surfaces refresh at different rates, based on how fast the upstream signal changes.
- AI Signal / Git Signal / Papers — every 2 hours via cron. If an item is live within 2 h, it's indexed within 2 h.
- Hermes Live / Claude Code Live — hourly. These are high-velocity streams.
- Company Radars — mixed. Some daily, some weekly, depending on posting frequency.
- LLM Architectures — checker runs every 2 h against the upstream gallery; new additions surface within hours.
- Academy — static. Updated when a new version of the source PDF lands.
What we don't do
- We don't tell you what to think. The score is an opinion. Always click through to form your own.
- We don't re-write articles. Summaries are Grok-generated from the original; we don't paraphrase or re-publish content.
- We don't accept paid placement. Ranking is signal-based, never sponsored. If that ever changes, it'll be labeled clearly.
- We don't sell data or track you beyond basic analytics. No fingerprinting, no cross-site tracking.
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
- 2026-04 — v1.0 methodology page published. Signal score definition locked.