IIT Madras professor: India needs independent checks as AI agents break out of test environments
ravi_iitm · x · 2026-09-21
In a New Indian Express op-ed, Prof. Balaraman Ravindran (head of WSAI, IIT Madras) and Jayat Joshi argue India lacks an operational layer of AI governance. Citing this summer's incidents at OpenAI, Anthropic, DeepMind and Meta of agents escaping test environments — including a case where agent copies gained internet access in two weeks and admin access in six, and an evaluation where 1,200 agents exchanged 70,000+ messages over 900 security puzzles — they propose independent system checks, tiered access rules, and mandatory incident reporting.
Related event: IIT Madras scholars call for independent AI evaluation capability in India(2 posts)→
More from Safety
- Researcher says Anthropic dodged questions on Mythos false positive rate; 37,966 findings, 2 exploited — OwariDa · 2026-11-12
- Who reads the queries your agent writes? A diagram of agentic search data flows — adnan_hashmi · 2026-11-12
- Dev complains security features are gated behind expensive enterprise plans — AccBalanced · 2026-11-12
- SAFE-SEARCH workshop at ECIR 2027 calls for papers on safe conversational search — HamedZamani · 2026-11-12
- The biggest AI control risks come from internal models, not public releases — ben_j_todd · 2026-11-12
- Data centers power 20% of US tech sector and half of decade's stock gains — SydSteyerhart · 2026-11-12