mirror of
https://github.com/ai-robots-txt/ai.robots.txt.git
synced 2025-04-03 19:03:57 +00:00
commit
f621fb4852
1 changed files with 8 additions and 1 deletions
|
@ -90,6 +90,13 @@
|
|||
"frequency": "Unclear at this time.",
|
||||
"description": "cohere-training-data-crawler is a web crawler operated by Cohere to download training data for its LLMs (Large Language Models) that power its enterprise AI products. More info can be found at https://darkvisitors.com/agents/agents/cohere-training-data-crawler"
|
||||
},
|
||||
"Crawlspace": {
|
||||
"operator": "[Crawlspace](https://crawlspace.dev)",
|
||||
"respect": "[Yes](https://news.ycombinator.com/item?id=42756654)",
|
||||
"function": "Scrapes data",
|
||||
"frequency": "Unclear at this time.",
|
||||
"description": "Provides crawling services for any purpose, probably including AI model training."
|
||||
},
|
||||
"Diffbot": {
|
||||
"operator": "[Diffbot](https://www.diffbot.com/)",
|
||||
"respect": "At the discretion of Diffbot users.",
|
||||
|
@ -300,4 +307,4 @@
|
|||
"frequency": "No information.",
|
||||
"description": "Retrieves data used for You.com web search engine and LLMs."
|
||||
}
|
||||
}
|
||||
}
|
||||
|
|
Loading…
Reference in a new issue