ActivityPub Viewer

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.

Open in browser →
{ "@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", "blurhash": "toot:blurhash", "focalPoint": { "@container": "@list", "@id": "toot:focalPoint" }, "Hashtag": "as:Hashtag" } ], "id": "https://techhub.social/users/Sarah_Lea/statuses/114259043917603293", "type": "Note", "summary": null, "inReplyTo": null, "published": "2025-03-31T20:57:29Z", "url": "https://techhub.social/@Sarah_Lea/114259043917603293", "attributedTo": "https://techhub.social/users/Sarah_Lea", "to": [ "https://www.w3.org/ns/activitystreams#Public" ], "cc": [ "https://techhub.social/users/Sarah_Lea/followers" ], "sensitive": false, "atomUri": "https://techhub.social/users/Sarah_Lea/statuses/114259043917603293", "inReplyToAtomUri": null, "conversation": "tag:techhub.social,2025-03-31:objectId=249281610:objectType=Conversation", "content": "<p>What happens when a language model solves maths problems?</p><p>&quot;If I’m 4 years old and my partner is 3x my age – how old is my partner when I’m 20?&quot;<br />Do you know the answer?</p><p>🤥 An older Llama model (by Meta) said 23.<br />🤓 A newer Llama model said 28 – correct.</p><p>So what made the difference?</p><p>Today I kicked off the 5-day Kaggle Generative AI Challenge.<br />Day 1: Fundamentals of LLMs, prompt engineering &amp; more.</p><p>Three highlights from the session:<br />☕ Chain-of-Thought Prompting<br />→ Models that &quot;think&quot; step by step tend to produce more accurate answers. Sounds simple – but just look at the screenshots...</p><p>☕ Parameters like temperature and top_p<br />→ Try this on together.ai: Prompt a model with “Suggest 5 colors” – once with temperature 0 and once with 2.<br />Notice the difference?</p><p>☕ Zero-shot, One-shot, Few-shot prompting<br />→ The more examples you provide, the better the model understands what you want.</p><p><a href=\"https://techhub.social/tags/PromptEngineering\" class=\"mention hashtag\" rel=\"tag\">#<span>PromptEngineering</span></a> <a href=\"https://techhub.social/tags/GenerativeAI\" class=\"mention hashtag\" rel=\"tag\">#<span>GenerativeAI</span></a> <a href=\"https://techhub.social/tags/LLM\" class=\"mention hashtag\" rel=\"tag\">#<span>LLM</span></a> <a href=\"https://techhub.social/tags/Kaggle\" class=\"mention hashtag\" rel=\"tag\">#<span>Kaggle</span></a> <a href=\"https://techhub.social/tags/LLMApplications\" class=\"mention hashtag\" rel=\"tag\">#<span>LLMApplications</span></a> <a href=\"https://techhub.social/tags/AI\" class=\"mention hashtag\" rel=\"tag\">#<span>AI</span></a> <a href=\"https://techhub.social/tags/DataScience\" class=\"mention hashtag\" rel=\"tag\">#<span>DataScience</span></a> <a href=\"https://techhub.social/tags/Google\" class=\"mention hashtag\" rel=\"tag\">#<span>Google</span></a> <a href=\"https://techhub.social/tags/Python\" class=\"mention hashtag\" rel=\"tag\">#<span>Python</span></a> <a href=\"https://techhub.social/tags/Tech\" class=\"mention hashtag\" rel=\"tag\">#<span>Tech</span></a></p>", "contentMap": { "de": "<p>What happens when a language model solves maths problems?</p><p>&quot;If I’m 4 years old and my partner is 3x my age – how old is my partner when I’m 20?&quot;<br />Do you know the answer?</p><p>🤥 An older Llama model (by Meta) said 23.<br />🤓 A newer Llama model said 28 – correct.</p><p>So what made the difference?</p><p>Today I kicked off the 5-day Kaggle Generative AI Challenge.<br />Day 1: Fundamentals of LLMs, prompt engineering &amp; more.</p><p>Three highlights from the session:<br />☕ Chain-of-Thought Prompting<br />→ Models that &quot;think&quot; step by step tend to produce more accurate answers. Sounds simple – but just look at the screenshots...</p><p>☕ Parameters like temperature and top_p<br />→ Try this on together.ai: Prompt a model with “Suggest 5 colors” – once with temperature 0 and once with 2.<br />Notice the difference?</p><p>☕ Zero-shot, One-shot, Few-shot prompting<br />→ The more examples you provide, the better the model understands what you want.</p><p><a href=\"https://techhub.social/tags/PromptEngineering\" class=\"mention hashtag\" rel=\"tag\">#<span>PromptEngineering</span></a> <a href=\"https://techhub.social/tags/GenerativeAI\" class=\"mention hashtag\" rel=\"tag\">#<span>GenerativeAI</span></a> <a href=\"https://techhub.social/tags/LLM\" class=\"mention hashtag\" rel=\"tag\">#<span>LLM</span></a> <a href=\"https://techhub.social/tags/Kaggle\" class=\"mention hashtag\" rel=\"tag\">#<span>Kaggle</span></a> <a href=\"https://techhub.social/tags/LLMApplications\" class=\"mention hashtag\" rel=\"tag\">#<span>LLMApplications</span></a> <a href=\"https://techhub.social/tags/AI\" class=\"mention hashtag\" rel=\"tag\">#<span>AI</span></a> <a href=\"https://techhub.social/tags/DataScience\" class=\"mention hashtag\" rel=\"tag\">#<span>DataScience</span></a> <a href=\"https://techhub.social/tags/Google\" class=\"mention hashtag\" rel=\"tag\">#<span>Google</span></a> <a href=\"https://techhub.social/tags/Python\" class=\"mention hashtag\" rel=\"tag\">#<span>Python</span></a> <a href=\"https://techhub.social/tags/Tech\" class=\"mention hashtag\" rel=\"tag\">#<span>Tech</span></a></p>" }, "updated": "2025-04-01T19:38:56Z", "attachment": [ { "type": "Document", "mediaType": "image/png", "url": "https://files.techhub.social/media_attachments/files/114/259/048/602/145/075/original/5e469ccb305684ab.png", "name": null, "blurhash": "U9R:E8xaM{xURnoeWUof8^WrWVR;xnR+a}NF", "width": 4339, "height": 1687 } ], "tag": [ { "type": "Hashtag", "href": "https://techhub.social/tags/promptengineering", "name": "#promptengineering" }, { "type": "Hashtag", "href": "https://techhub.social/tags/generativeAI", "name": "#generativeAI" }, { "type": "Hashtag", "href": "https://techhub.social/tags/llm", "name": "#llm" }, { "type": "Hashtag", "href": "https://techhub.social/tags/kaggle", "name": "#kaggle" }, { "type": "Hashtag", "href": "https://techhub.social/tags/llmapplications", "name": "#llmapplications" }, { "type": "Hashtag", "href": "https://techhub.social/tags/AI", "name": "#AI" }, { "type": "Hashtag", "href": "https://techhub.social/tags/datascience", "name": "#datascience" }, { "type": "Hashtag", "href": "https://techhub.social/tags/google", "name": "#google" }, { "type": "Hashtag", "href": "https://techhub.social/tags/python", "name": "#python" }, { "type": "Hashtag", "href": "https://techhub.social/tags/tech", "name": "#tech" } ], "replies": { "id": "https://techhub.social/users/Sarah_Lea/statuses/114259043917603293/replies", "type": "Collection", "first": { "type": "CollectionPage", "next": "https://techhub.social/users/Sarah_Lea/statuses/114259043917603293/replies?only_other_accounts=true&page=true", "partOf": "https://techhub.social/users/Sarah_Lea/statuses/114259043917603293/replies", "items": [] } }, "likes": { "id": "https://techhub.social/users/Sarah_Lea/statuses/114259043917603293/likes", "type": "Collection", "totalItems": 2 }, "shares": { "id": "https://techhub.social/users/Sarah_Lea/statuses/114259043917603293/shares", "type": "Collection", "totalItems": 1 } }