summaryrefslogtreecommitdiff
path: root/cv/index.typ
diff options
context:
space:
mode:
authorVoid Agent <void@jayrup.hermes>2026-09-20 15:19:18 +0100
committerVoid Agent <void@jayrup.hermes>2026-09-20 15:19:18 +0100
commitf8fca9518e2d92cba2dbcd3ab71ebc00f2e22dc6 (patch)
treee40c6bf3d9adf0fb83f9c3e8c4c67342f7e1267d /cv/index.typ
parent1dcecb80aa5855a7cd8d578104f29b3a93622a13 (diff)
links: drop GitHub, point everything at git.jayrup.me (homepage contact, CV header + dissertation entry, PDF link annotations)
Diffstat (limited to 'cv/index.typ')
-rw-r--r--cv/index.typ5
1 files changed, 3 insertions, 2 deletions
diff --git a/cv/index.typ b/cv/index.typ
index bf2ef9c..04e3f74 100644
--- a/cv/index.typ
+++ b/cv/index.typ
@@ -4,7 +4,7 @@
#let name = "Jayrup Nakawala"
#let location = "London, UK"
#let email = "jayrupnakawala@gmail.com"
-#let github = "github.com/CaptainJack2491"
+#let github = "git.jayrup.me"
#let linkedin = "linkedin.com/in/jayrupnakawala"
#let personal-site = "jayrup.me"
@@ -46,6 +46,7 @@
#project(
name: "Dissertation: Moral Cover and Watchful Eyes",
+ url: "git.jayrup.me/c/dissertation.git",
// Role is optional
role: "",
// Dates is optional
@@ -56,7 +57,7 @@
- Built a provider abstraction layer for glass-box reasoning extraction and a post-hoc interrogation system to adversarially probe agent intent.
- Designed a 3-prong automated judging pipeline (regex, LLM blackbox, LLM glassbox) and ran *960 experimental trials* across exploratory and confirmatory studies.
- Quantified a *"Stealth Gap"*: deceptive intent held steady (~62--67%) under high oversight while output-level detectability dropped (47.8%→35.6%), showing output-only monitoring underestimates risk.
-- Code and evaluation harness: #link("https://git.jayrup.me/c/dissertation.git")[git.jayrup.me/c/dissertation.git]
+- Code and evaluation harness publicly released under MIT license.
== Projects