mirror of
https://github.com/ai-robots-txt/ai.robots.txt.git
synced 2025-04-04 11:03:59 +00:00
Fix typo and trigger rerun of main job
This commit is contained in:
parent
83c8603071
commit
38a388097c
2 changed files with 7 additions and 7 deletions
|
@ -34,7 +34,7 @@ for section in soup.find_all("div", {"class": "agent-links-section"}):
|
|||
|
||||
default_values = {
|
||||
"Unclear at this time.",
|
||||
"No information. provided.",
|
||||
"No information provided.",
|
||||
"No information.",
|
||||
"No explicit frequency provided."
|
||||
}
|
||||
|
|
12
robots.json
12
robots.json
|
@ -1,14 +1,14 @@
|
|||
{
|
||||
"AI2Bot": {
|
||||
"description": "Explores 'certain domains' to find web content.",
|
||||
"frequency": "No information. provided.",
|
||||
"frequency": "No information provided.",
|
||||
"function": "Content is used to train open language models.",
|
||||
"operator": "[Ai2](https://allenai.org/crawler)",
|
||||
"respect": "Yes"
|
||||
},
|
||||
"Ai2Bot-Dolma": {
|
||||
"description": "Explores 'certain domains' to find web content.",
|
||||
"frequency": "No information. provided.",
|
||||
"frequency": "No information provided.",
|
||||
"function": "Content is used to train open language models.",
|
||||
"operator": "[Ai2](https://allenai.org/crawler)",
|
||||
"respect": "Yes"
|
||||
|
@ -17,14 +17,14 @@
|
|||
"operator": "Amazon",
|
||||
"respect": "Yes",
|
||||
"function": "Service improvement and enabling answers for Alexa users.",
|
||||
"frequency": "No information. provided.",
|
||||
"frequency": "No information provided.",
|
||||
"description": "Includes references to crawled website when surfacing answers via Alexa; does not clearly outline other uses."
|
||||
},
|
||||
"anthropic-ai": {
|
||||
"operator": "[Anthropic](https://www.anthropic.com)",
|
||||
"respect": "Unclear at this time.",
|
||||
"function": "Scrapes data to train Anthropic's AI products.",
|
||||
"frequency": "No information. provided.",
|
||||
"frequency": "No information provided.",
|
||||
"description": "Scrapes data to train LLMs and AI products offered by Anthropic."
|
||||
},
|
||||
"Applebot": {
|
||||
|
@ -66,14 +66,14 @@
|
|||
"operator": "[Anthropic](https://www.anthropic.com)",
|
||||
"respect": "Unclear at this time.",
|
||||
"function": "Scrapes data to train Anthropic's AI products.",
|
||||
"frequency": "No information. provided.",
|
||||
"frequency": "No information provided.",
|
||||
"description": "Scrapes data to train LLMs and AI products offered by Anthropic."
|
||||
},
|
||||
"ClaudeBot": {
|
||||
"operator": "[Anthropic](https://www.anthropic.com)",
|
||||
"respect": "[Yes](https://support.anthropic.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler)",
|
||||
"function": "Scrapes data to train Anthropic's AI products.",
|
||||
"frequency": "No information. provided.",
|
||||
"frequency": "No information provided.",
|
||||
"description": "Scrapes data to train LLMs and AI products offered by Anthropic."
|
||||
},
|
||||
"cohere-ai": {
|
||||
|
|
Loading…
Reference in a new issue