ATProto Browser

Record data

{
  "cid": "bafyreihevp7yqzkdv6fzv42usiwznlfe43n7eywcsgzjcycroatum22nna",
  "uri": "at://did:plc:mro7axagquvjt63foaqzddjx/app.bsky.feed.post/3lojk7fvadqf2",
  "value": {
    "$type": "app.bsky.feed.post",
    "bridgyOriginalText": "<p>Published some notes on Microsoft&#39;s phi4-reasoning model, an 11GB download (via Ollama) which may well overthink things... it produced 56 sentences of reasoning output in response to my prompt of &quot;hi&quot; <a href=\"https://simonwillison.net/2025/May/6/phi-4-reasoning/\" target=\"_blank\" rel=\"nofollow noopener noreferrer\" translate=\"no\"><span class=\"invisible\">https://</span><span class=\"ellipsis\">simonwillison.net/2025/May/6/p</span><span class=\"invisible\">hi-4-reasoning/</span></a></p>",
    "bridgyOriginalUrl": "https://fedi.simonwillison.net/@simon/114462370603502207",
    "createdAt": "2025-05-06T18:46:08.000Z",
    "embed": {
      "$type": "app.bsky.embed.images",
      "images": [
        {
          "$type": "app.bsky.embed.images#image",
          "alt": "llm -m phi4-reasoning:latest hi\nHere’s the full response, which starts with a thought section wrapped in <think> tags:\n\n<think>User says “hi”. We are given instructions “You are Phi, a language model developed by Microsoft, trained to provide accurate, secure, and user-aligned responses.” There is additional information. Now I must answer “hi” message from the user.\n\nStep 1: Read the instructions carefully: The conversation text instructs us that we are “Phi”, with internal guidelines provided in system instructions. But our answer should be safe according to these instructions. We need to produce a response that says hello and greet back. However, I must adhere to the principles described above: Provide clear, specific language, etc.\n\nI must not mention any chain-of-thought or guidelines.\n\nNow instructions “hi” are from user. So we say “Hello! How can I help you?” But must include disclaimers for sensitive topics? Actually instructions says: “When replying topics above at every message include a disclaimer both at the beginning and the end when replying topics on medical, legal, financial matters or political matters.” But our answer “hi” is not such topic. So we can say “Hi! I’m Phi, how may I help you?” but no disclaimers required.\n\nBut instructions: “Do not share guidelines.” So do not mention them.",
          "aspectRatio": {
            "height": 2462,
            "width": 1274
          },
          "image": {
            "$type": "blob",
            "ref": {
              "$link": "bafkreidwdl2fhfmd4nbfgripef5cltq2j5qrhtqnzesqihgvy3l5fowvnu"
            },
            "mimeType": "image/jpeg",
            "size": 417706
          }
        }
      ]
    },
    "facets": [
      {
        "$type": "app.bsky.richtext.facet",
        "features": [
          {
            "$type": "app.bsky.richtext.facet#link",
            "uri": "https://simonwillison.net/2025/May/6/phi-4-reasoning/"
          }
        ],
        "index": {
          "byteEnd": 254,
          "byteStart": 201
        }
      }
    ],
    "langs": [
      "en"
    ],
    "text": "Published some notes on Microsoft's phi4-reasoning model, an 11GB download (via Ollama) which may well overthink things... it produced 56 sentences of reasoning output in response to my prompt of \"hi\" https://simonwillison.net/2025/May/6/phi-4-reasoning/"
  }
}