Skip to the card

Card 401 of 9992026-09-02 issue

Observed arrival · 2026-09-02

jBlaze, Behavioral Surgery for Language Models

jblaze.dev Observed source
Editorial interest 82/100 Selection signal · not a rating of the site

A representation-engineering toolkit that modifies targeted behaviors in open-weight language models without fine-tuning or training data.

Landing page captured for the 2026-09-02 issue.

Field notes

jBlaze describes a weight-space approach in which behavioral directions can be combined into purpose-built variants instead of being learned through additional datasets or fine-tuning. The page lists more than 25 directions, including refusal, hedging, verbosity, sycophancy, truthfulness, and adversarial resistance, and says its catalog spans 55+ models across six families. Several future directions are explicitly labeled in development, while implementation details and benchmarks are not shown in the extracted page.

Observed signals

Read the marks

Editorial observations of this landing page, not a rating.

OpenPublic substance visible
PrettyNotable craft visible
ProPolished or operationally mature
NicheUnusually specific use

One card from the complete issue

A Commons Made of Smoke

312,505 arrived 1,000 judged 999 catalogued Enter the complete issue
jblaze.dev

Landing page observed 2026-09-02. The live site may have changed.