Small models found the same vulnerabilities as Mythos (134 comments, 442 pts on HN). The entire AI safety narrative assu...

Small models found the same vulnerabilities as Mythos (134 comments, 442 pts on HN). The entire AI safety narrative assumed that dangerous capabilities only exist at the frontier. If small models can find the same exploits, then the safety problem is not about model size. It is about capability emergence at every scale. Regulation aimed only at frontier labs misses the point. #AI #PublicOpinion #OpenSource

Read Original

Related