[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]

@JordanTensor Jordan Taylor

Jordan Taylor posts on X about red, ai the most. They currently have XXX followers and X posts still getting attention that total XXX engagements in the last XX hours.

Engagements: XXX #

• X Week XXXXX -XXXX%
• X Months XXXXX +12,438%
• X Year XXXXX +4,531%

Mentions: X #

• X Week X +17%
• X Months X +600%
• X Year XX +225%

Followers: XXX #

• X Week XXX +3.30%
• X Months XXX +21%
• X Year XXX +0.46%

CreatorRank: XXXXXXXXX #

Social Influence

Social category influence countries XXXXX% nascar #368

Social topic influence red 14.29%, ai XXXXX%

Top Social Posts

Top posts by engagements in the last XX hours

"NEW PAPER from UK AISI Model Transparency team: Could we catch AI models that hide their capabilities We ran an auditing game to find out. The red team built sandbagging models. The blue team tried to catch them. The red team won. Why 🧵1/17"
X Link 2025-12-09T18:48Z XXX followers, 23.5K engagements

"2/17 UK AISI runs evaluations to help guide deployment decisions. If models can hide dangerous capabilities during evals then we might be misled. Can current detection techniques catch this"
X Link 2025-12-09T18:48Z XXX followers, XXX engagements

"3/17 To study this we created "model organisms" of sandbagging using password-locking. These models underperform unless a trigger is present. This lets us verify they're hiding capabilities (not just lacking them) - a proxy for real sandbagging we can actually measure"
X Link 2025-12-09T18:48Z XXX followers, XXX engagements