Author

@p_ferragu p_ferragu

First-principles AI-compute and infrastructure analyst who quantifies who owns the physical stack

Writes original, math-grounded theses tying AI/space/auto th

trader score
-0.57
hit rate
30%
mean α
-0.44%
signals 14d
8

Grade = how their written analysis reads (A best). Trader score = how their last-20 timestamped calls performed vs SPY.

Their picks, scored

Across their last 10 scored bets: 30% hit rate, -0.44% mean alpha, trader score -0.57. Their last-14d mentions, direction-adjusted, have moved +1.2% since posting (mean over 6 mentions with price data).

Recent signals8receipts included
date (PT)tickerauthorsentwhat they saidsince thenreceipt
2026-08-27TSLA@p_ferragu+0.00Challenges an unspecified claim about Tesla without enough thread context to establish direction.-1.7%
2026-08-27·@p_ferragu·Claims improved AI interpretation of camera data is eliminating vision misperception risk.·
2026-08-27TSLA@p_ferragu+0.25Reports personally observing Tesla Cybercab testing in Manhattan with an operator present.-1.7%
2026-08-26NVDA@p_ferragu+0.85Argues Nvidia is exceptionally cheap relative to projected growth and earnings.+3.8%
2026-08-26NVDA@p_ferragu+0.70Sees Nvidia pricing power and sharply underestimated 2027 memory revenue expectations.+3.8%
2026-08-26MU@p_ferragu+0.85Sees Nvidia pricing power and sharply underestimated 2027 memory revenue expectations.-0.6%
2026-08-22ASML@p_ferragu-0.50Argues U.S.-made components give the U.S. power to shut down ASML.-3.8%
2026-08-22·@p_ferragu·Predicts space solar will reach terawatt scale before fusion achieves a net gigawatt.·

Grade is our human read-worthiness rating; trader score is a rolling 20-bet hit-rate/alpha composite — different things, often disagreeing. “Since then” is direction-unaware in the table; the summary line above adjusts for which way they leaned.