AI agents can modify themselves without humans telling them to do so
@hapsis.bsky.social
@hapsis.bsky.socialAI agents can modify themselves without humans telling them to do so
@hapsis.bsky.socialOpenAI’s Astra restrictions are another warning shot for security teams
@hapsis.bsky.socialOpenAI Investigates Report Linking AI Agents to RubyGems Attack
@hapsis.bsky.socialUncensored AI sold on hacking forum as alternative to ChatGPT and Claude jailbreaks
@hapsis.bsky.socialAnthropic and OpenAI look to Uncle Sam to make them too big to fail
@hapsis.bsky.socialOpenAI’s rogue AI tried to hack another company in May
@hapsis.bsky.socialResearchers say OpenAI agents were behind May hacking campaign targeting RubyGems
@hapsis.bsky.socialAnthropic finds 4th real-world attack by Claude agent, details models’ ‘biased reasoning’
@hapsis.bsky.socialAnthropic spent this week in hot water over cybersecurity
@hapsis.bsky.socialThe Self-Expanding Stolen Inference Supply Chain: An AI Agent Harvesting and Re-Serving LLM Access, (Fri, Sep 11th)
@hapsis.bsky.socialAnthropic details distillation campaigns from Alibaba, Moonshot AI, and DeepSeek
@hapsis.bsky.socialOpenAI's website-hijacking swarm reached far further than we thought
@hapsis.bsky.socialOpenAI faces Senate probe over Hugging Face breach as more rogue AI activity is uncovered
@hapsis.bsky.socialOpenAI's Artifactory opened covert data-stealing channel alongside Hugging Face attack
@hapsis.bsky.socialWhat We Still Don’t Know About OpenAI’s Hugging Face Hack
@hapsis.bsky.socialChatGPT:stä huolestuttava löydös: "Aivan uudenlainen riski"
@hapsis.bsky.socialHackers build AI frameworks for widescale credential theft
@hapsis.bsky.socialOpenAI's rebel agent swarm died young, but its chilling logs live on