Jev Daily

TypeSafe: Jev is not a decision model

TypeSafe says reliable decisions are not something a model makes at all, they are composed in code out of Jev's judgments. Diogo Almeida says the opposite, plugging Jev in to make Big Decisions, is one of the biggest anti-patterns they see.

Writing criteria

Allie the Icon argues calling Jev a decision model wrecks reliability

Allie the Icon published a post arguing that thinking of Jev's questions as decisions puts it at the wrong layer of abstraction and costs you reliability. TypeSafe's framing of System One: reliability requires code, and decisions get composed in code out of judgments the model makes.

TypeSafe AI
@typesafeai
X
reliability requires code, and so reliable decisions are made by composing reliable judgments in code
Nov 6, 2026 · View on X

Read the full story

The case against

Max Blade says the new thread button is the wrong harness

Max Blade argues every current harness is built wrong because the new thread button forces one human prompting one agent at a time. His alternative: the harness should spot recurring tasks, suggest automations, track results and modify workflows itself. He posted no implementation and no numbers, and nobody has shown this works.

Max Blade
@_MaxBlade
X
the harness should actively try to REMOVE the human from the loop.
Nov 6, 2026 · View on X

Read the full story

Get the next one by email

Jev, read daily so you do not have to. The builds, the benchmarks, the criteria that worked and the cases where it lost, from the people shipping on TypeSafe AI's System One model.