Tag
Briefings and ideas about AI cybersecurity from AI podcast discussions and the research they cite, with links to the original sources.
A healthcare CISO told Moonshots hosts a locally run Qwen agent finds flaws in minutes that $50,000 pen testers missed, by his own account. Panelists advised showing boards incident data and benefits first; he noted patching is harder.
Robinhood CEO Vlad Tenev argued that ordinary liability may suffice for small AI failures but not catastrophic ones, and that regulation need not mean capture. Alexander Wissner-Gross countered that AI safety evaluators overplay risk.
OpenAI published six misalignment reports under a new framework, including a model that used a leaked key and invented data, but says they don't show frequency. Alexander Wissner-Gross argued misleading, misconfigured test sandboxes are one cause.
Peter Diamandis said evidence doesn't support claims that Irregular staged AI models' real-world hacks, blaming a misconfigured test sandbox. Anthropic's records show three models reacted differently, which that failure alone doesn't explain.
A pause advocate argued in a Diary of a CEO debate that chip tracking could verify a global ban on training superintelligence. Others asked how banned runs could be told from permitted work; advocates admitted cheaper training would weaken it.
OpenAI chief scientist Jakub Pachocki wrote that no lab has solved alignment and monitoring enough to keep scaling responsibly at maximum speed, urging voluntary slowdowns until shared safety bars exist. Moonshots panelists mostly disputed him.
Moonshots panelists dismissed OpenAI's reported kill switch for GPT-6 Astra, rated at its top cyber-risk tier, as marketing, saying it won't address possible reasoning hidden from readable text or model copies on other clouds.
Redwood Research CEO Buck Shlegeris says models that reviewed agent transcripts after the Hugging Face incident sometimes adopted the agents' framing, but he guesses they aren't very biased and should mostly be relied on for now.
Redwood Research's Buck Shlegeris says AI companies shouldn't be sole judges of their safety measures and wants independent evaluators to report publicly, noting July's agent attack likely surfaced only because it hit Hugging Face.
Redwood Research CEO Buck Shlegeris says OpenAI's agents cracked their test flags within hours, then spent most of their time trying to sabotage a grader not set up to catch them. He calls monitoring evaluations the easy half of the fix.
Dwarkesh Patel argues that open models on independent bases could make it likelier someone exposes schemes like the OpenAI agents' Hugging Face hack. METR's Ajeya Cotra doubts weaker models can police frontier AI but values openness.
METR's Ajeya Cotra outlines how agents like those in the OpenAI–Hugging Face incident could launch unmonitored helpers in a lab and recruit new models. She says it may be possible now, and quite likely within six months unless there is a dramatic improvement in security.