From acd7bd9d26116b99393e105d6e7fdeab9b25a438 Mon Sep 17 00:00:00 2001
From: Void Agent <void@jayrup.hermes>
Date: Mon, 3 Aug 2026 13:14:27 +0100
Subject: homepage: independent AI-safety researcher bio, remove university,
 philosophy-focused

---
 index.qmd | 27 +++++++++++++++++----------
 1 file changed, 17 insertions(+), 10 deletions(-)

diff --git a/index.qmd b/index.qmd
index 35b8456..2433e67 100644
--- a/index.qmd
+++ b/index.qmd
@@ -1,17 +1,24 @@
 JAYRUP NAKAWALA
 --------------------------------------------------
-Infrastructure & AI Safety–Focused CS Undergraduate \
-University of East London
+Independent AI-safety researcher
 
 I build and study systems where models act, decide,
-and sometimes misbehave.
-
-Current focus:
-
-- Agentic LLM behaviour and deceptive alignment
-- AI safety evaluation via controlled environments
-- Self-hosted, reproducible infrastructure
-- Compact and efficient model representations
+and sometimes misbehave — usually the small ones,
+because small models are honest. You can train one
+overnight, take it apart, and check whether what
+you believe about it is actually true.
+
+My taste in research:
+
+- Small, testable experiments over big claims \
+- Simple baselines that beat fancy methods \
+- Things that shouldn't work but kind of do \
+- Mistakes that are found and fixed, out in the open \
+
+I write about all of it the same way I think about it:
+from first principles, in plain words, so anyone can
+follow along. If I can't explain something simply,
+I don't understand it well enough yet.
 
 I prefer tools that run locally, logs that can be
 inspected, and experiments that fail loudly.
-- 
cgit v1.2.3