Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

An early-access test of TypeSafe's Jev

Independent early-access trial of Jev that measures its calibrated judgments and reports cost per decision.

Articleresearch
Open source ↗

This summary is based on how curated lists describe the project; its README was not available to review.

Overview

A blog post on lindfors.no giving a first look at TypeSafe's Jev during early access. Per the listing, the author measures how well Jev's calibrated judgments hold up and works out the resulting cost per decision.

It is useful as an outside perspective from before broad availability.

What the decision model decides

TypeQuestionAnswers
OtherHow good and how costly are Jev's judgments in practice?(inferred)—

How it works

  1. Run test decisions on early-access Jev
  2. Measure calibration
  3. Compute cost per decision

Strengths

  • Independent perspective

Caveats

  • Early-access version; results may differ now
  • Only list summary available

At a glance

Type
Article
Status
research

Use cases and integrations

How curated lists describe it

  • Independent trial: measures calibrated judgments on early-access Jev and reports the resulting cost per decision.

    yibie/awesome-jev

Frequently asked questions

What is measured?

Calibrated judgments and cost per decision.

Is it independent?

Yes, it is a third-party trial.

Where is it?

https://lindfors.no/blog/a-first-look-at-typesafes-jev

Related projects

  • jevcheck

    pytest-style tool that pins fixtures and expected Jev answers, then fails a model upgrade when answers flip or confidence drops.

    ProjectbetaPython
  • jevoss

    Test harness for any Jev-API decision model: accuracy, calibration and robustness probes for reordering, injection and padding.

    ServicebetaPython
  • can-jev-play

    Experiments testing whether Jev can spot positive-expected-value dice bets from payout tables, and whether recent wins or losses sway it.

    Projectresearch
  • Jev × LexGLUE

    Zero-shot run of Jev 1.13 on all seven LexGLUE legal tasks (23,607 examples) versus GPT-5.6 Luna, open models and fine-tuned BERT.

    ProjectresearchPython
  • Jev vs GPT-4.1 on a synthetic survey

    Pre-specified study running Jev and GPT-4.1 as 300 synthetic survey respondents; question format mattered more than model.

    ProjectresearchPython
  • jev-acento

    Pre-registered paired audit of Jev on Spanish across 3,200 labelled items, plus a CLI to rerun it on your own data.

    CLIresearchPython