Automated README summary
Automatically summarized from the README on 24 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A browser Tetris versus game where you play Jev or Laya, or watch the two bots face off, with garbage, spins, combos and back-to-back chains under TETR.IO-style rules.
How it uses Jev
Code finds all reachable placements, ranks them and keeps a shortlist of 14. Jev is asked which measured outcome it wants (lines_sent, holes_created, well_depth, cancels_incoming, combo_after), returning probabilities used to pick the move; next-piece decisions are prefetched a piece ahead.
Primitives:choice
Technique worth stealing
Ask the model to choose among measured outcomes of a code-generated shortlist, and prefetch the next decision while the current piece is still falling.
Try it
./play.sh starts Laya and the game server and opens http://localhost:8081; npm test runs offline.
Model judgments from README excerpts
Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.
Models & evaluation dates
- Inclusion gate
jev-1.14.0- Project signals
jev-1.14.0- Category
jev-1.14.0- Pattern tags
jev-1.14.0
Evidence
These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.
- Jev is core to the projectFound in material0.67
- Shows a System One patternFound in material0.84
- Describes handling uncertaintynot found in the excerpt0.03
- Reports measured numbersnot found in the excerpt0.03
- Is a runnable toolFound in material0.82
- Top-10 learning shortlist signalunclear0.41
- Is a replica of the modelunclear0.48
- Solves a common problem (0–2)score on a 0–2 scale0.01 / 2
- About JevFound in material0.99
no-judgment band (0.40–0.60)
no-judgment band (0.40–0.60)
The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 24 Oct 2026.