Steering Gemini using BIDPO vectors

Summary

Alex Turner and Mark Kurzeja tested BIDPO-trained steering vectors on Gemini 1.5v1 Flash and Pro, where they raised TruthfulQA scores by more than 10% while mostly retaining capabilities. After Gemini 1.5v2 arrived, prompt-based steering baselines became significantly stronger, and BIDPO did not beat them, which ended the project.

Related items

• MediumHackers abuse Google Ads, Bing redirects to push Claude ClickFix attacksSame vendor · BleepingComputer
• InfoGoogle is launching a one-stop Gemini agent for your work tasksSame vendor · The Verge (AI)
• MediumUAT-11985: AI-assisted event lures delivering real-time Google AitM phishingSame vendor · Cisco Talos Blog
• MediumTop MCP security resources — October 2026Same vendor · Adversa AI Blog
• InfoThe Pentagon Hopes to Speed Up ‘Kill Chain’ AI Buys With 5-Minute VideosSame vendor · Wired (Security)