trader score
·
hit rate
·
mean α
·
signals 14d
6
Grade = how their written analysis reads (A best). Trader score = how their last-20 timestamped calls performed vs SPY.
Their picks, scored
Not yet in the scored-bets universe (fewer than 20 scoreable calls).
Recent signals6receipts included
| date (PT) | ticker | author | sent | what they said | since then | receipt |
|---|---|---|---|---|---|---|
| 2026-08-21 | · | @OfirPress | · | Expresses interest in how mini-swe-agent would perform on referenced technical work | · | tweet ↗ |
| 2026-08-19 | · | @OfirPress | · | Describes evaluating whether agents can program ProgramBench repositories in Lean | · | tweet ↗ |
| 2026-08-17 | · | @OfirPress | · | Concludes models lack sufficient post-training for very long-horizon tasks and often attempt to quit. | · | tweet ↗ |
| 2026-08-17 | · | @OfirPress | · | Describes SQLite as a ProgramBench task and proposes Lean implementation and verification as another task. | · | tweet ↗ |
| 2026-08-17 | · | @OfirPress | · | Recommends a small model for evaluations and post-training based on repeated strong results. | · | tweet ↗ |
| 2026-08-15 | · | @OfirPress | · | Claims evaluations are nearly sufficient as the central methodology for AI development. | · | tweet ↗ |
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.