TechCrunch · AI· Aditya Mehta·· 8 d ago
Goodfire says its new ‘inside-out’ monitors catch rogue AI agents at a fraction of the cost
Goodfire says its new ‘inside-out’ monitors catch rogue AI agents at a fraction of the cost
AI summary
Goodfire just launched what it says is a cheaper way to keep AI agents in check: Instead of paying a second AI to read everything an agent does, its monitors peek inside the model while it works and only call in backup when something looks fishy.
Selection record
Threshold 76Media and individualsFirst 62Second 58
Not admittedSum of both 120 < twice the threshold 152
- Source tier
- Media and individuals; this tier's threshold is 76
- Pre-filter
- passed：AI智能体监控与可解释性技术
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: TechCrunch · AI · techcrunch.com