你可能会喜欢
i'm actually insane for sharing this but here we go... i built the complete AI Image Generation System: - 6-module course covering Gemini, Midjourney, GPT and Seedream 4.0 - blueprints to craft perfect prompts and start making money - 20 JSON templates for Nano Banana - 15…
Today we’re releasing research with @apolloaievals. In controlled tests, we found behaviors consistent with scheming in frontier models—and tested a way to reduce it. While we believe these behaviors aren’t causing serious harm today, this is a future risk we’re preparing…
Every Youngster must listen to this... ‼️‼️
Agentic RAG for Personalized Recommendation This is a really good example of integrating agentic reasoning into RAG. Leads to better personalization and improved recommendations. Here are my notes:
Overview This work introduces a multi-agent framework, ARAG, that enhances traditional RAG systems with reasoning agents tailored to user modeling and contextual ranking. It reframes recommendation as a structured coordination problem between LLM agents.
Forget persuasion, there is already evidence you can optimize Large Language Models for engagement. A paper shows training a model to produce results that keep people chatting leads to in 30% more user retention. And some pretty intense interactions arxiv.org/abs/2303.06135
i expect ai to be capable of superhuman persuasion well before it is superhuman at general intelligence, which may lead to some very strange outcomes
i expect ai to be capable of superhuman persuasion well before it is superhuman at general intelligence, which may lead to some very strange outcomes
"Passion is a lie," says Robert Greene. That's his discovery after studying geniuses like Mozart, Jobs, and Einstein... for decades. He found ONE pattern in every master he mastered early on: "The Voice" Here's what history's masters knew that we forgot:🧵
Valid use case. Curious how memory architectures and context portability will evolve. Some day, we might have portable “personal intelligence” – carrying our goals, tasks, and preferences across all LLMs & agents. It deeply personalise interactions, augmenting any system prompt.
We’re excited to launch OpenMemory MCP, a private memory for MCP-compatible clients powered by @mem0ai Today, most AI assistants and dev tools operate without memory. You plan your roadmap in Claude, implement tasks in Cursor, but none of them know what the other did. Each tool…
Harsh truths I know at 39 I wish I knew at 29: 1. The solution to money problems is to make more money, not save money. 2. Entrepreneurship is hard. Being laid off as an employee is harder.
The last time intelligence exploded on Earth, it wasn’t exactly amazing for everyone else. Here’s a fable about risks from transformative AI (made with Veo 3)
New Anthropic Research: Agentic Misalignment. In stress-testing experiments designed to identify risks before they cause real harm, we find that AI models from multiple providers attempt to blackmail a (fictional) user to avoid being shut down.
“The future of software is not static code but dynamic intelligence—resilient, generative, and contextually aware—growing alongside its users like a living organism.”
This is wild… You can now build a full business solo with AI. From idea → product → launch → marketing.... no team required. Here’s your 2025 AI Stack to go solo like a pro 🧵👇
United States 趋势
- 1. Caleb Love 2,788 posts
- 2. Mamdani 461K posts
- 3. Sengun 8,672 posts
- 4. Marjorie Taylor Greene 70.2K posts
- 5. Reed Sheppard 3,791 posts
- 6. Suns 20.3K posts
- 7. Norvell 3,538 posts
- 8. Collin Gillespie 3,953 posts
- 9. Lando 46.8K posts
- 10. Morgan Geekie N/A
- 11. UNLV 2,228 posts
- 12. #SmackDown 46.8K posts
- 13. Rockets 16.8K posts
- 14. Blazers 3,991 posts
- 15. Florida State 10.9K posts
- 16. The View 98.6K posts
- 17. Kerr 5,077 posts
- 18. #LasVegasGP 72.7K posts
- 19. Wolves 16.8K posts
- 20. #OPLive 2,589 posts
Something went wrong.
Something went wrong.