Post-Cutoff

Alex Volkov: Jev as an instant compaction plugin for Claude

Alex Volkov @altryneX

Why it matters

Viral demo (1.2M views) of Jev scoring tool calls to shrink a Claude session’s context.

Summary

Volkov shows a community plugin (tamaratran/fast-jev-compaction) that uses Jev to score and drop unnecessary tool calls; he says it took about 1 second to cut a Claude session from nearly 1M to 86K tokens. User-reported, not benchmarked.

Metrics read 2026-09-29 via api.fxtwitter.com: 1,164,277 views, 8,403 likes.

Archived text

This is actually insane. This uses @typesafeai Jev model, as a plugin in Claude to review all the un-nesseasary tool calls, and it takes 1s to run!

Like, literally, 1 second to take my Claude session from nearly 1M to ... 86K tokens! 😮

Ask your claude to install it and be amazed

Use this prompt

``` Install, and configure : https://github.com/tamaratran/fast-jev-compaction

```

Quoting @tamarajtran: found the perfect use case for @typesafeai Jev:

instant compaction

in 2026, why is compaction still a summarization prompt?

Jev can make it instant by scoring every tool call and dropping what’s irrelevant

Source: x.com/altryne/status/2100739055923425589Archived 2026-09-29 via fxtwitter (unofficial).Counts: 1,164,285 views, 8,403 likes, 464 reposts, 164 replies (at fetch time)Media: image 1, image 2

Cited in

  1. Model releases 77 days after the cutoff

    TypeSafe AI releases Jev, a ‘System One’ decision model that returns typed probabilities instead of text