Tracking AI existential risk. Auto-aggregated headlines. Human-curated analysis.
AGGREGATING 47 SOURCES · UPDATED LIVE
Research

Towards surfacing model algorithms with meta-tokens in the J-Space

Zac Boring July 20, 2026 1 min read
Read original source →

TL;DRWe used J-lens on Qwen3.6-27B to find “meta-tokens”: tokens that surface non-obvious computation in the model. When the model reads ambiguous text, 什么意思 ("what does this mean") fires in the J-space, and steering it away makes the model answer "a boiled egg every morning is hard to beat" with nutrition facts instead of catching the pun. On LCM problems, "gcd" fires, pointing at the product/GCD algorithm: swapping the GCD vector from 9 to 3 makes the model change its answer for the LCM of 27

By agam_bhatia

Read the full article at Alignment Forum →