Add 'brainsteam/content/annotations/2023/01/29/1674988872.md'
continuous-integration/drone/push Build is passing Details

This commit is contained in:
ravenscroftj 2023-01-29 10:45:08 +00:00
parent 986aec8960
commit 5bc0ad7daa
1 changed files with 60 additions and 0 deletions

View File

@ -0,0 +1,60 @@
---
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.