jevbooks

← All projects

jev-plays-tetris

pedroarruda07/jev-plays-tetris

Automating Tetris with Jev (TypeSafe AI)

Game & Simulation0.96Runner-up: Agent DecisionsFunnelInspection
Automated README summary

Automatically summarized from the README on 25 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

A responsive TypeScript Tetris game with an independent, typed game engine. It lets Jev, the TypeSafe AI "System One" model, play autonomously by choosing piece placements.

How it uses Jev

Jev chooses a final placement for each piece. The local planner searches legal paths and provides each TypeSafe criterion with hold usage, landing piece and cells, resulting board after row removal, and board-shape measurements (holes, column heights, maximum height, aggregate height, bumpiness). Jev selects a placement ID via the TypeSafe Choice API; the controller rechecks reachability and executes the chosen path one normal game input at a time.

Primitives:choice

Technique worth stealing

Using a typed Choice API to select among precomputed legal placements, with the model inferring consequences from board state and rules.

Try it

Set JEV_API_KEY in .env, run npm install and npm run dev, then click "Let Jev play" or press J.

View on GitHub

Start using Jev: API key and your first request →

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-1.13.0
Project signals
jev-1.13.0
Category
jev-1.13.0
Pattern tags
jev-1.13.0

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 projectunclear0.47
  • Shows a System One patternnot found in the excerpt0.08
  • Describes handling uncertaintynot found in the excerpt0.03
  • Reports measured numbersnot found in the excerpt0.04
  • Is a runnable toolFound in material0.96
  • Top-10 learning shortlist signalnot found in the excerpt0.21
  • Is a replica of the modelnot found in the excerpt0.15
  • Solves a common problem (0–2)score on a 0–2 scale0.01 / 2
  • About JevFound in material0.94
Signals
Jev is core to the project0.47Shows a System One pattern0.08Describes handling uncertainty0.03Reports measured numbers0.04Is a runnable tool0.96Top-10 learning shortlist signal0.21Is a replica of the model0.1500.51Solves a common problem (0–2)0.01 / 2012

no-judgment band (0.40–0.60)

Design patterns
Inspection0.85Funnel0.70Fail open, fail closed0.67Menu0.48Scorecard0.28Viewfinder0.2000.51

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 25 Sept 2026.