Introducing RAT: Retrieval Argument Thinking. Extract just the reasoning process from deepSeek-r1 and send it to any LLM via OpenRouter. Boost the second LLM's performance and gain access to missing capabilities like function calling and JSON mode. 👇

Finally found a way I can blow $200 in a weekend

Deepseek 70B Distill + Groq LPU Sleep can wait. Build fast! 🚀💪👀

PMing with o1 pro, v0, and DeepSeek-R1 The days of just writing specs are over. AI can now generate detailed PRDs in minutes. The future belongs to technical PMs who can design and build, not just document.

This is the entire code needed to reproduce R1 lol Hundreds of Billions of Dollars Later

Is it realistic for us to expect Anthropic for a better pricing plan?👀

so apparently a lot of influential tech/vc folks like Chamath Palihapitiya, Naval, Jared Friedman fell for this great but still misleading (i believe not intentionally) blog post by Jeffrey Emanuel the blog post is very detailed, forms a cohesive narrative, and is *mostly* correct (except for

We are now have super models like o3. Any plan at least open sourcing archaic older models like gpt3? Sam Altman

Everyone should be using this website to understand the inside of an LLM. I'm surprised more people don't know about it. Benjamin Bycroft made this beautiful interactive visualization to show exactly how the inner workings of each of the weights of an LLM work. Here's a link:

Emails should not be stuck in the past. Sign up for the new.email waitlist today. new.email

🪁🦜CoAgents x LangGraph Bring your agents into React apps with powerful and fully customizable React hooks. Styled or headless UI. Including Agentic Chat, realtime Shared State, Frontend tools, Generative UI, and Human-in-the-Loop. Used by Fortune 100 teams & thousands of

Introducing our AI co-scientist, a multi-agent AI system built with Gemini 2.0. We think of it as a virtual collaborator for scientists, using advanced reasoning to synthesize a huge amount of literature, generate novel hypotheses, and suggest detailed research plans. We’re

i’ve said this in private convos so I’ll say it here… “better memory” is the final unlock we need to get truly better agents, and 2025 is when we’ll see more of this we have strong reasoning, tools for tools, plenty of frameworks, but memory/context management needs

We need MCP server for GitBook

Three new state-of-the-art audio models in the API: 🗣️ Two speech-to-text models—outperforming Whisper 💬 A new TTS model—you can instruct it *how* to speak 🤖 And the Agents SDK now supports audio, making it easy to build voice agents. Try TTS now at OpenAI.fm.

Alright, it’s finally here! Meet Aligno – a premium Framer SaaS template crafted to elevate SaaS businesses. For the next 24 hours, I’m giving it away FREE! Just like, repost, and comment "Aligno" below, and I’ll DM you the link. (Make sure you’re following so I can DM you)

In last 6 months, I’ve coded 18 MVPs for clients using Cursor. Here’s my full workflow: → Cursor Project Rules → Gemini Pro 2.5 for context → Sonnet 3.5 for execution → CodeGuide for docs Bookmark this and copy my Cursor AI workflow: ↓

Lesson #1: "A startup should perpetually operate at the edge of instability." Most founders try to build perfect systems. But operational perfection is actually premature optimization that kills innovation. The tension of "controlled chaos" is where breakthroughs happen.

I compiled 200+ n8n automation templates you can copy & paste into your business or sell to other companies. Just straight plug-and-play systems for: – Lead gen -Content creation – Email outreach – CRM updates – AI workflows – Slack/Discord bots …and more. Follow + Reply