← Back to Model Beat
Other·Sep 29·all news from September 29, 2026

Anthropic Says It Discovered a Crispr-Like System. Now What?

Anthropic researchers have identified a potential method for editing the internal activations of large language models, a technique they compare to the gene-editing tool Crispr. While the company suggests this could improve model safety and interpretability, outside experts have noted that the findings are currently preliminary and await further experimental verification.

Covered by 1 source

Related stories

OtherSenator introduces bill to protect workers during AI boomOct 1 · 5 sourcesOtherCan we predict the jobs robots will do?Sep 30OtherAI Talent Race Between US and China Is the Next BattlegroundOct 2OtherGetting the Source Right, Not Just the Fact: Source-Aware Verification for MCP AgentsSep 29