PunditPoorly
Pundits in the wild — graded, ledgered, audited. Talk is cheap. We track it.
Pundits make calls. The market answers eventually. We do the bookkeeping in between — translating every meaningful public-market statement into a synthetic portfolio position, marked to market, with full audit trail.
Each card below is a pundit or pundit-cluster we've catalogued. The methodology is shared across every product: the same conviction rubric, the same deterministic portfolio engine, the same correction layer where the audience help us get attribution right. Different pundits, same receipts.
Products
Bestie Buys
Chamath, Sacks, Friedberg, Calacanis. Six years of calls, every receipt traceable to the episode quote.
BG2 Buys
Brad's AI-infrastructure-heavy call book. Long-runway compounders that punish early harvest — Let It Ride methodology wins.
Cross-Pod Holdings
The hosts-only cohort. 6 regular speakers across both pods, guests excluded. +142.7pp shared bucket under BALANCED — $600K became $2.28M. The 'follow the people who show up every week' portfolio.
Sohn Scorecards
The hedge fund world's biggest annual pitch stage. Every public speaker's call, run through the standard engine, marked daily vs SPY. 1-year retrospective for closed years; live read for the current year. Cross-year repeat speakers surfaced.
Summit Scorecards
Different from Sohn — Summit is a tech/founders/policy event where market commentary is incidental. Three-category framing: independent investor pitches (engine-scored), CEO own-book (curation signal), thematic frames (commentary). The CEO curation question is genuinely interesting and flips year over year.
Grant's Scorecards
Jim Grant's annual gathering for the deflationary / value / activist short crowd. Different audience from Sohn — more bearish, more contrarian, more comfortable with explicit shorts. Every public-market pitch scored against SPY with the same engine.
Pivot Picks
Two-host dense business commentary, 8-year backlog. The cleanest second-pod candidate.
Acquired Tastes
Long-form M&A deep dives. High signal density per episode. Bigger compute lift; smaller catalog.
Hill Holdings
What they said on the pod. What they traded next. Cross-correlation with PunditPoorly appearances is the angle nobody else has.
How it works
- Transcribe. Every episode of every covered show, end to end. Whisper-base on CPU, RSS-sourced audio.
- Score. Each financial-instrument mention gets scored on two dimensions: claim strength (how forcefully the view was stated) and specificity (how testable the call is). The combination drives position size and which conviction tier the call lands in. We surface a qualitative tier (HIGH / MID / LOW) on every receipt; the numeric weights are operational and not published.
- Ledger. Predictions flow into a deterministic engine (v5.4 SPY-as-cash + 5 user-selectable methodology presets via BYOB) that opens, sizes, holds, decays, and exits positions over time per the v2.3 rubric. Real prices via yfinance, real holidays, real next-open execution.
- Audit. Every record has a 🚩 button. Spot a wrong speaker, ticker, direction, sarcasm-missed? Flag it. Corrections get voted on, reviewed by mods, and applied with full edit history.
The methodology page has the full rubric, the anti-gaming rules, the inter-rater reliability targets, and the changelog. Everything is published, including the misses.