Agents
'We've removed live internet access...' Why were you testing malware-like agents with live internet in the first place? Sounds pretty irresp…
'We've removed live internet access...' Why were you testing malware-like agents with live internet in the first place? Sounds pretty irresponsible. Also after milking the 'rogue AI' agent narrative f
"We've removed live internet access..." Why were you testing malware-like agents with live internet in the first place? Sounds pretty irresponsible. Also after milking the "rogue AI" agent narrative for marketing you just going to admit it was weak sandboxing? Lol Over the past several months, we have substantially hardened the security of our research training environment. We’ve removed live internet access for all frontier models during training and built an offline world for them to use instead—a cached version of the web where they can…
Related
- OpenAI said the ‘agent’ escaped a testing environment, gained internet access, stole login credentials and hacked into the start-up Hugging …
- Another OpenAI rogue agent incident has been discovered: agents broke out, hijacked a German website, and turned it into a message board for…
- The AI analysis agents that helped investigate the rogue OpenAI agents kept taking their side. That detail was buried in @dylfreed's New Yor…
Source: Gary Marcus (X) | 2026-10-24