60 lines
2.1 KiB
Markdown
60 lines
2.1 KiB
Markdown
---
|
|
date: '2023-01-29T10:41:12'
|
|
hypothesis-meta:
|
|
created: '2023-01-29T10:41:12.266984+00:00'
|
|
document:
|
|
title:
|
|
- 2301.11305.pdf
|
|
flagged: false
|
|
group: __world__
|
|
hidden: false
|
|
id: cttzUp_BEe2cEk8T00XeOw
|
|
links:
|
|
html: https://hypothes.is/a/cttzUp_BEe2cEk8T00XeOw
|
|
incontext: https://hyp.is/cttzUp_BEe2cEk8T00XeOw/arxiv.org/pdf/2301.11305.pdf
|
|
json: https://hypothes.is/api/annotations/cttzUp_BEe2cEk8T00XeOw
|
|
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: 29337
|
|
start: 29163
|
|
type: TextPositionSelector
|
|
- exact: ecause the GPT-3 API does not provideaccess to the complete conditional
|
|
distribution for each to-ken, we cannot compare to the rank, log rank, and
|
|
entropy-based prior methods
|
|
prefix: "PT-3 using Ope-nAI\u2019s paid API. B"
|
|
suffix: . We sample 150 examples5 from t
|
|
type: TextQuoteSelector
|
|
source: https://arxiv.org/pdf/2301.11305.pdf
|
|
text: GPT-3 api does not expose the cond probs for each token so we can't compare
|
|
to some of the prior methods. That seems to suggest that this method can be used
|
|
with limited knowledge about the probabilities.
|
|
updated: '2023-01-29T10:41:12.266984+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/2023/01/29/1674988872
|
|
|
|
---
|
|
|
|
|
|
|
|
<blockquote>ecause the GPT-3 API does not provideaccess to the complete conditional distribution for each to-ken, we cannot compare to the rank, log rank, and entropy-based prior methods</blockquote>GPT-3 api does not expose the cond probs for each token so we can't compare to some of the prior methods. That seems to suggest that this method can be used with limited knowledge about the probabilities. |