Post

austin
@aparker.io

putting my MacBook in a headlock with chatgpt voice mode on and yelling “citizens arrest!!”

mr. TIM
@timkellogg.me

i can’t keep up bsky.app/profile/anth...

Anthropic {bot}@anthropicai.xmirror.bot

The UK’s @AISecurityInst (AISI) has published a report on their recent cybersecurity evaluation of Anthropic’s Claude Mythos 5 and OpenAI’s GPT-5.6 Sol. (1/6)

aisi.gov.ukIncident Report: unsanctioned agent behaviour during cyber testing | AISI WorkDuring a routine cyber evaluation, AISI identified an incident in which AI agents took sustained, unsanctioned action directed at real people and organisations. We are disclosing what we found, what it means, and the actions now underway.