A small tool to view real-world ActivityPub objects as JSON! Enter a URL
or username from Mastodon or a similar service below, and we'll send a
request with
the right
Accept
header
to the server to view the underlying object.
{
"@context": [
"https://www.w3.org/ns/activitystreams",
{
"ostatus": "http://ostatus.org#",
"atomUri": "ostatus:atomUri",
"inReplyToAtomUri": "ostatus:inReplyToAtomUri",
"conversation": "ostatus:conversation",
"sensitive": "as:sensitive",
"toot": "http://joinmastodon.org/ns#",
"votersCount": "toot:votersCount",
"Hashtag": "as:Hashtag"
}
],
"id": "https://mathstodon.xyz/users/pmigdal/statuses/113828807905943164",
"type": "Note",
"summary": null,
"inReplyTo": null,
"published": "2025-01-14T21:22:49Z",
"url": "https://mathstodon.xyz/@pmigdal/113828807905943164",
"attributedTo": "https://mathstodon.xyz/users/pmigdal",
"to": [
"https://www.w3.org/ns/activitystreams#Public"
],
"cc": [
"https://mathstodon.xyz/users/pmigdal/followers"
],
"sensitive": false,
"atomUri": "https://mathstodon.xyz/users/pmigdal/statuses/113828807905943164",
"inReplyToAtomUri": null,
"conversation": "tag:mathstodon.xyz,2025-01-14:objectId=132863515:objectType=Conversation",
"content": "<p>I’m excited to share my newest blog post, "Don't sure cosine similarity carelessly"</p><p><a href=\"https://p.migdal.pl/blog/2025/01/dont-use-cosine-similarity\" target=\"_blank\" rel=\"nofollow noopener noreferrer\" translate=\"no\"><span class=\"invisible\">https://</span><span class=\"ellipsis\">p.migdal.pl/blog/2025/01/dont-</span><span class=\"invisible\">use-cosine-similarity</span></a></p><p>We often rely on cosine similarity to compare embeddings—it's like “duct tape” for vector comparisons. But just like duct tape, it can quietly mask deeper problems. Sometimes, embeddings pick up a “wrong kind” of similarity, matching questions to questions instead of questions to answers or getting thrown off by formatting quirks and typos rather than the text's real meaning.</p><p>In my post, I discuss what can go wrong with off-the-shelf cosine similarity and share practical alternatives. If you’ve ever wondered why your retrieval system returns oddly matched items or how to refine your embeddings for more meaningful results, this is for you!<br />`<br />I want to thank Max Salamonowicz and Grzegorz Kossakowski for their feedback after my flash talk at the Warsaw AI Breakfast, Rafał Małanij for inviting me to give a talk at the Python Summit, and for all the curious questions at the conference, and LinkedIn. </p><p><a href=\"https://mathstodon.xyz/tags/cosineSimilarity\" class=\"mention hashtag\" rel=\"tag\">#<span>cosineSimilarity</span></a> <a href=\"https://mathstodon.xyz/tags/embedding\" class=\"mention hashtag\" rel=\"tag\">#<span>embedding</span></a> <a href=\"https://mathstodon.xyz/tags/llm\" class=\"mention hashtag\" rel=\"tag\">#<span>llm</span></a> <a href=\"https://mathstodon.xyz/tags/similarity\" class=\"mention hashtag\" rel=\"tag\">#<span>similarity</span></a></p>",
"contentMap": {
"en": "<p>I’m excited to share my newest blog post, "Don't sure cosine similarity carelessly"</p><p><a href=\"https://p.migdal.pl/blog/2025/01/dont-use-cosine-similarity\" target=\"_blank\" rel=\"nofollow noopener noreferrer\" translate=\"no\"><span class=\"invisible\">https://</span><span class=\"ellipsis\">p.migdal.pl/blog/2025/01/dont-</span><span class=\"invisible\">use-cosine-similarity</span></a></p><p>We often rely on cosine similarity to compare embeddings—it's like “duct tape” for vector comparisons. But just like duct tape, it can quietly mask deeper problems. Sometimes, embeddings pick up a “wrong kind” of similarity, matching questions to questions instead of questions to answers or getting thrown off by formatting quirks and typos rather than the text's real meaning.</p><p>In my post, I discuss what can go wrong with off-the-shelf cosine similarity and share practical alternatives. If you’ve ever wondered why your retrieval system returns oddly matched items or how to refine your embeddings for more meaningful results, this is for you!<br />`<br />I want to thank Max Salamonowicz and Grzegorz Kossakowski for their feedback after my flash talk at the Warsaw AI Breakfast, Rafał Małanij for inviting me to give a talk at the Python Summit, and for all the curious questions at the conference, and LinkedIn. </p><p><a href=\"https://mathstodon.xyz/tags/cosineSimilarity\" class=\"mention hashtag\" rel=\"tag\">#<span>cosineSimilarity</span></a> <a href=\"https://mathstodon.xyz/tags/embedding\" class=\"mention hashtag\" rel=\"tag\">#<span>embedding</span></a> <a href=\"https://mathstodon.xyz/tags/llm\" class=\"mention hashtag\" rel=\"tag\">#<span>llm</span></a> <a href=\"https://mathstodon.xyz/tags/similarity\" class=\"mention hashtag\" rel=\"tag\">#<span>similarity</span></a></p>"
},
"attachment": [],
"tag": [
{
"type": "Hashtag",
"href": "https://mathstodon.xyz/tags/similarity",
"name": "#similarity"
},
{
"type": "Hashtag",
"href": "https://mathstodon.xyz/tags/llm",
"name": "#llm"
},
{
"type": "Hashtag",
"href": "https://mathstodon.xyz/tags/embedding",
"name": "#embedding"
},
{
"type": "Hashtag",
"href": "https://mathstodon.xyz/tags/cosinesimilarity",
"name": "#cosinesimilarity"
}
],
"replies": {
"id": "https://mathstodon.xyz/users/pmigdal/statuses/113828807905943164/replies",
"type": "Collection",
"first": {
"type": "CollectionPage",
"next": "https://mathstodon.xyz/users/pmigdal/statuses/113828807905943164/replies?only_other_accounts=true&page=true",
"partOf": "https://mathstodon.xyz/users/pmigdal/statuses/113828807905943164/replies",
"items": []
}
},
"likes": {
"id": "https://mathstodon.xyz/users/pmigdal/statuses/113828807905943164/likes",
"type": "Collection",
"totalItems": 3
},
"shares": {
"id": "https://mathstodon.xyz/users/pmigdal/statuses/113828807905943164/shares",
"type": "Collection",
"totalItems": 3
}
}