Live and recent posts from across the Fediverse tagged #patternlabs, aggregated by home.social.
@camwilson “What is noteworthy is how OpenAI's models did it without being explicitly asked.”
How was that confirmed? If OAI reps say this I’m inclined to not believe them.
Q Are the break-ins part of the startup #Irregular hacking efforts?
#PatternLabs / #DanLahav ex IBM / #OmerNevo ex google / #Sequoia #ShaunMaguire #DeanMeyer / #CyberOffensive <https://www.cnbc.com/2026/08/09/israeli-startup-irregular-linked-to-ai-hacks-openai-anthropic-meta.html>
“Founded three years ago and based in Tel Aviv, Irregular is a niche player in artificial intelligence, backed with $80 million from Sequoia and #RedpointVentures and valued last year at $450 million. Its technology serves as a sort of #cybersecurity test bed for AI models.
With the leading models becoming ever more powerful, their ability to act in malicious ways is turning into a major threat for corporations and governments, especially as the risk involves hacking into critical computer #systems and #infrastructure. The recent exploits at OpenAI, Anthropic and Meta all involved their AI models accessing websites that should have been off-limits as part of the cybersecurity testing.
#Irregular’s name kept coming up because it was identified as hosting the so-called evaluation testbed.”
Meanwhile #VC money is having a two-way bet; Money on #AI; Money on #hacking AI-models… I mean *cough* #Pentesting *cough*
#PatternLabs / #DanLahav ex IBM / #OmerNevo ex google / #Sequoia #ShaunMaguire #DeanMeyer / #CyberOffensive / #AIModel #AIKillSwitch <https://www.cnbc.com/2026/08/09/israeli-startup-irregular-linked-to-ai-hacks-openai-anthropic-meta.html>