Automated README summary
Automatically summarized from the README on 25 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A 3D simulated valley of rabbits, deer and wolves where each animal's hourly action is chosen by Jev rather than scripted, with a live browser viewer, replay files and benchmark tooling for Python 3.11+.
How it uses Jev
Each valley hour, every animal sends Jev a Choice question over its state (hunger, thirst, nearby animals) to pick its action, plus Score questions (alertness, prey weakness, chase effort) and Noul questions (breeding, whether a wolf attacks). Returned probabilities drive behaviour; low confidence can freeze an animal, and any failed call stops the run.
Primitives:choicescorenoul
Technique worth stealing
Score the model's extra answers against ground truth and treat low confidence as hesitation rather than guessing.
Try it
export TYPESAFE_API_KEY, then python -m valley live --seed 7 --days 2 --open
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 material0.99
- Shows a System One patternFound in material0.98
- Describes handling uncertaintyFound in material0.97
- Reports measured numbersnot found in the excerpt0.31
- Is a runnable toolunclear0.46
- Top-10 learning shortlist signalFound in material0.64
- Is a replica of the modelnot found in the excerpt0.16
- Solves a common problem (0–2)score on a 0–2 scale0.04 / 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 25 Oct 2026.