Further evidence for @GaryMarcus 's worries about the security competence of the people running AI. Vibe coding without then checking securi…

Further evidence for @GaryMarcus 's worries about the security competence of the people running AI. Vibe coding without then checking security is not impressive 🚨 Attackers stole a METR API key and used it for three weeks, consuming credits worth about $600,000. A fail-open bug disabled Google authentication on a public agent dashboard. The attacker prompted an agent to reveal the key and added SSH persistence. How the exposed app was a…

⚠️ AI agents are wildly premature technology that is being rolled out way too fast. The deepest lesson about the vibe coded AI agent disaste…
this is … odd. the whole problem with agentic code is that people wind up with hard to debug redundancies, security holes, deleted databases…
There’s been a lot of debate and speculation about the Hugging Face attack over the last month, and many people have been understandably ske…
“Not so much agent civilizations doing crazy things as OpenAI ignoring fundamental security prectices as it turned out.”
New from @Reuters: the OpenAI agent that hacked into Hugging Face also compromised code that a customer was running on @Modal. “We’re aware …

Source: Gary Marcus (X) | 2026-09-02

Related