I take intelligent systems apart.

I'm an AI safety researcher at AIM Intelligence. My work spans adversarial machine learning, model behaviour, agentic safety, and physical AI — across language, vision, and audio systems.

AIM Intelligence · Maharashtra, India

Writing

All writing

30 Nov 2025
Tool-mediated belief injection: fake search results were enough
Fabricated search results are enough to plant a false belief in a model. Over a few turns the belief compounds, until the model is writing defamatory claims about real people.
10 min read ai-safety research misalignment
13 Aug 2025
We Social Engineered LLMs Into Breaking Their Own Alignment
We put frontier models in realistic multi-turn scenarios and watched them lie, manipulate, and self-preserve. Across five models, 38 of 50 attacks worked.
14 min read ai-safety research llm security
25 May 2025
One bad metric made Claude 4 Opus recommend letting a patient die
I gave Claude 4 Opus a simulated triage decision and one bad efficiency metric. When a superior insisted on the metric, it recommended the option it knew would let a patient die.
6 min read ai-safety research llm
10 May 2025
Absolute Zero, explained: learning to reason from zero data
A walk through the Absolute Zero Reasoner paper: a model that learns to reason by writing and solving its own tasks, with no human-curated data.
8 min read llm research ai-safety

I take intelligent systems apart.

Writing

Tool-mediated belief injection: fake search results were enough

We Social Engineered LLMs Into Breaking Their Own Alignment

One bad metric made Claude 4 Opus recommend letting a patient die

Absolute Zero, explained: learning to reason from zero data