#interpretability

2 stories

#ai agents #ai monitoring #ai safety #technology #ai alignment #ai deception #ai oversight #anthropic #baseten #goodfire #hugging face incident #open models

Goodfire's cheaper AI monitors catch rogue agents inside
A startup launches internal monitoring probes that watch AI models work from within, costing a fraction of traditional oversight methods.
TechCrunch · 2m
Can AI police rogue AI agents?
As AI agents grow more autonomous, companies are deploying AI to monitor AI, but the approach raises thorny questions about deception and oversight.
TechCrunch · 2m