Jamie's NLP Just Got a Lot Smarter (Thanks, DeepSeek V4)

原始 JSON

{
  "kind": 30023,
  "id": "347c3d765012c38e48678038fa85ff567489cb36f1452a68a1ca943a34f7ced7",
  "pubkey": "4535551a40271b059ab92b71e7ab7e8700061a2d91b0d20f313ef82f052eb085",
  "created_at": 1777420863,
  "tags": [
    [
      "client",
      "Yakihonne",
      "31990:20986fb83e775d96d188ca5c9df10ce6d613e0eb7e5768a0f0b12b37cdac21b3:1700732875747"
    ],
    [
      "published_at",
      "1777420224"
    ],
    [
      "d",
      "No6fL6ES1CLTWq0vBSiEh"
    ],
    [
      "image",
      "https://image.nostr.build/4d74fa7d1cd37352e05f6678994c9d4cef67b731d66e789c0dc62b5efb9cb45c.jpg"
    ],
    [
      "title",
      "Jamie's NLP Just Got a Lot Smarter (Thanks, DeepSeek V4)"
    ],
    [
      "summary",
      "Jamie Pull upgraded to DeepSeek V4. Multi-angle podcast research, better proper-noun search, Deep/Fast modes. Same 10¢ pricing. Structured output for AI agents, playable clips for humans. L402 Lightning payable, zero setup."
    ],
    [
      "t",
      "deepseekv4"
    ],
    [
      "t",
      "deepseek"
    ],
    [
      "t",
      "lightning"
    ],
    [
      "t",
      "l402"
    ],
    [
      "t",
      "machine payments"
    ],
    [
      "t",
      "bitcoin"
    ],
    [
      "t",
      "Open Source"
    ]
  ],
  "content": "**TL;DR:** Jamie Pull just upgraded to V2 powering \"Deep Mode\" with DeepSeek V4. Multi-angle podcast research, better proper-noun search, same 10-cent pricing. \n\n[Web App](https://www.pullthatupjamie.ai/app?view=agent) | [Agent Quick Start](https://www.pullthatupjamie.ai/llms.txt)\n\n## What's New\n\nWith Jamie Pull's V2 Release - Deep Research mode x Deepseek V4 is running the show.\n\nWe swapped in DeepSeek's open-source V4 model for search and synthesis. It's a 1.6 trillion parameter Mixture-of-Experts beast that costs a fraction of what closed models charge. V4-Flash runs at $0.14 per million tokens while matching GPT-4 class performance. That's 268x cheaper than Claude Opus.\n\nAll those savings? We reinvested them into making Jamie search harder and think deeper.\n\nMulti-angle research, not just \"here's the top result\"\n\nWhen you ask Jamie a question now, it explores the topic from multiple angles. Ask about CBDCs and you'll get the Bitcoin maximalist take, the Fed perspective, the privacy angle, the developing-world view. Comprehensive answers, not just first-match-wins.\n\n## Deep vs Fast: Choose Your Best Fit\n\nWe give you two ways to ask. Deep mode (the default) throws our most capable models at your question—multi-step reasoning, cross-referenced sources, the works. You'll wait 60-90 seconds for that thoroughness. \n\n ![image](https://image.nostr.build/75fa476fd0cbaa937dda387e650d6ed1f2c55a7ad834807755150b3f0de4d2e8.png)\n\nFast mode runs a leaner, single-pass answer in 30-45 seconds. Perfect for quick lookups or questions you mostly know the answer to. The kicker: both cost the same per call. No premium tier, no upcharge for \"thinking harder.\" \n\n## Why This Matters\n\nOpen-source models are eating the world. DeepSeek V4 dropped on April 24th with MIT-licensed weights and benchmark scores that rival or beat GPT-5 and Claude Opus on coding tasks. But it costs pennies on the dollar.\n\nThat price gap isn't just academic. It's what lets us run deeper, more comprehensive searches without charging you $50/month.\n\nSame 10 cents per call. More angles explored. Better answers.\n\nTry It:\n- [Web App](https://www.pullthatupjamie.ai/app?view=agent)\n- [Agent Quick Start](https://www.pullthatupjamie.ai/llms.txt)\n\nStill L402 Lightning payable. Still zero setup. Just better. \n\n## FAQ\n\n### What changed?\nWe upgraded to DeepSeek V4, reinvested the cost savings into deeper multi-angle search, and fixed proper noun matching. Same price, better answers.\n\n### What's the difference between Deep and Fast mode?\nDeep mode uses our most capable models for multi-step reasoning and cross-referenced sources (~60-90 seconds). Fast mode runs lighter models for single-pass answers (~30-45 seconds). Same price per call. Pick Deep for thorough research, Fast for quick lookups. You can switch between them mid-conversation with one tap.\n\n### Is it more expensive now?\nNope. Still 10 cents per research call.\n\n### What's DeepSeek V4?\nOpen-source 1.6 trillion parameter model that matches GPT-4/Claude quality at a fraction of the cost. MIT licensed, released April 24th, 2026.\n\n### Will this work with AI agents?\nYes. Hit the /api/pull endpoint with L402 auth. You get back structured JSON with timestamps, clips, and metadata. No hallucination, just actual quotes with audio proof.[Agent Quick Start API Docs](https://www.pullthatupjamie.ai/llms.txt) .\n\n### Can I try it without paying?\nYes. The web app has free trial credits. Just go to https://pullthatupjamie.ai/app?view=agent and ask a question.\n\n",
  "sig": "4cca2de53dc7d21ebc7bbf66b5f21866ba78cb242cc8500e4d9e9ee4dbf8fe19f2c2c449ae03fc9bc020a55ad521240505610ec146ab23f2fb1e1060b3f749d0"
}