brainsteam.co.uk/brainsteam/content/annotations/2023/01/29/1674989511.md

58 lines
1.8 KiB
Markdown

---
date: '2023-01-29T10:51:51'
hypothesis-meta:
created: '2023-01-29T10:51:51.599889+00:00'
document:
title:
- 2301.11305.pdf
flagged: false
group: __world__
hidden: false
id: 7-zzGp_CEe2jCu-eEdGdsw
links:
html: https://hypothes.is/a/7-zzGp_CEe2jCu-eEdGdsw
incontext: https://hyp.is/7-zzGp_CEe2jCu-eEdGdsw/arxiv.org/pdf/2301.11305.pdf
json: https://hypothes.is/api/annotations/7-zzGp_CEe2jCu-eEdGdsw
permissions:
admin:
- acct:ravenscroftj@hypothes.is
delete:
- acct:ravenscroftj@hypothes.is
read:
- group:__world__
update:
- acct:ravenscroftj@hypothes.is
tags:
- chatgpt
- detecting gpt
target:
- selector:
- end: 40642
start: 40509
type: TextPositionSelector
- exact: ex-tending DetectGPT to use ensembles of models for scoring,rather than
a single model, may improve detection in theblack box setting
prefix: 'lts in Section 5.2 suggest that '
suffix: . Another topic that remains une
type: TextQuoteSelector
source: https://arxiv.org/pdf/2301.11305.pdf
text: DetectGPT could be extended to use ensembles of models allowing iot to work
in black box settings where the log probs are unknown
updated: '2023-01-29T10:51:51.599889+00:00'
uri: https://arxiv.org/pdf/2301.11305.pdf
user: acct:ravenscroftj@hypothes.is
user_info:
display_name: James Ravenscroft
in-reply-to: https://arxiv.org/pdf/2301.11305.pdf
tags:
- chatgpt
- detecting gpt
- hypothesis
type: annotation
url: /annotations/2023/01/29/1674989511
---
<blockquote>ex-tending DetectGPT to use ensembles of models for scoring,rather than a single model, may improve detection in theblack box setting</blockquote>DetectGPT could be extended to use ensembles of models allowing iot to work in black box settings where the log probs are unknown