AI Briefing
Slowly, then fast. Every morning.
A daily AI briefing, newsletter and podcast for early-stage investors: what happened, what holds up, and what it means, with occasional deep dives.
Current release
- v0.2.50-beta, public code commit
db244c204ad4(2026-11-01T23:56:03Z) - Latest edition: 2026-11-02 · 28 editions and 18 deep dives published
- Deep dive the same day: read or listen
- Status exported 2026-11-02T13:20:49Z by the project's own pipeline
Release notes
v0.2.50-beta · 2026-11-02 (weekday slot)
- Money section: up to five funding, deal and valuation stories (a deal word plus a stated amount) get their own "Money" block in the briefing, email and site, between Recommended reading and In brief.
- One chart a day: the write stage asks for a 3-6 bar chart from one Must-read story; every value must appear in that story's own sources or no chart is made. Shown under the story in the email and on the site, labelled "Figures as reported in this story's sources." (
analysis.chart: falseturns it off.) - Dashboard phase 3: Briefings shows email time and count, takes status and corrections per day, with the rebuild action folded under Maintenance; Sources leads with failing sources and folds the queue and history; Runs shows the last 14 with a health line and folds older runs; Subscribers has one channel summary and folds manual sends and list management.
- Fixes found by the ship check: gift links carrying any
*_tokenparameter (a Washington Postpwapi_tokenJWT reached the staging site and the privacy scan stopped the release) are cleaned like other tracking parameters; the chart accepts a story number returned as text ("2") and logs why no chart was made.
v0.2.49-beta · 2026-11-02 (weekday slot)
- Core beliefs, first refresh (Steven approved all six proposals, 2026-11-01; doc "Core Beliefs: Proposed Updates"): thesis 16 says containment is conceptual until proven; view 5 adds founders' liability; view 15 warns against writing off incumbents on early cannibalisation; new view 22, "Human provenance or ruin"; perspective.md adds robotics and AI-driven science, agent-to-agent authority, and a liability-and-insurance diligence rule.
How it is made
Curated sources
Lab and company posts, trade press, researchers and newsletters, every feed verified live before it is used.
Evidence first
Each story is weighed by what kind of source backs it; every Must read gets an evidence check, and figures that trace to no source are looked up or cut before anything is sent.
Local first
Runs each morning with local models for most stages and Claude for the critical pass and editing; voiced locally.
Release gate
Nothing goes out (site, podcast, email) unless tests, a secrets scan, privacy checks and a human approval of sensitive changes have passed. Changes reach production as releases.
Current focus
Beta: aggressive fact checking before email and audio, wider source coverage; podcast listing after four green weeks.
Repository freshness
See the latest hub observation. A current repository comparison has not yet been loaded.