✳flâneur — a map of the web's best reading
Why I'm Not a Security Doomer - by Miles Brundage
milesbrundage.substack.com · 4,177 words · saved by 1 readers
Preventing theft of AI systems is hard. But sometimes it's worth it, and protecting model weights specifically is a good target.
Why I'm Not a Security Doomer Preventing theft of AI systems is hard. But sometimes it's worth it, and protecting model weights specifically is a good target. Miles Brundage Mar 11, 2025 27 6 Share I have recently – in a somewhat joke-y way – started using the term “security doomer.” By security doomer, I mean people who think that AI systems can’t be protected from theft by sophisticated state attackers, or at least that protecting them would slow down AI research so much that it isn’t worth the effort. This is a reasonable perspective, since securing anything against sophisticated attackers
Explore this link on the map →related reading
- AI 2027ai-2027.com
- Nova DasSarma on why information security may be critical to the safe development of AI systems | 80,000 Hours80000hours.org
- IIIb. Lock Down the Labs: Security for AGI - SITUATIONAL AWARENESSsituational-awareness.ai
- AI 2027ai-2027.com
- Cybersecurity Looks Like Proof of Work Nowdbreunig.com
- An Action Plan for American Leadership in AI | IFPifp.org
- Off Target | CNAScnas.org
- A basic systems architecture for AI agents that do autonomous research — LessWronglesswrong.com
- My picture of the present in AI — LessWronglesswrong.com
- Fields that I reference when thinking about AI takeover prevention — LessWronglesswrong.com
- Nonproliferation — Chapter 5 of Superintelligence Strategynationalsecurity.ai
- A Safe Path to Open Weights - Thinking Machines Labthinkingmachines.ai