I Pun Daddy

Hoje é dia de recarregar baterias💪 Bom domingo a todos !

manual traders are literally getting slaughtered while this automated scanner tracks exactly what prediction market whales are buying claude just wired up a live script hunting specific arbitrage gaps between polymarket and limitless on the 15 minute charts the raw python code is completely open source on stream so you can finally stop acting like retail exit liquidity

You’re using your brain WRONG. In 2010, Stanford neurologist Dr Frank Longo gave a 2-hour lecture on how memory really works. Everything you’ve learned about memory is mostly wrong. His frameworks: • The Magic 7 rule • How sleep moves memories to storage • Use it or lose it

ANDREJ KARPATHY WAS RIGHT. THIS 40-MINUTE Y COMBINATOR LECTURE PROVES IT we're in the 1960s of LLMs most people using Claude have the wrong mental model Software 3.0. LLMs as operating systems how to actually think about and work with them save this 👇

DeepSeek V4 + Claude Code is actually insane 🤯 Claude Code is the hands. DeepSeek V4 is the big robot brain. Now it can build, fix, test, and refactor code like it drank 12 coffees. No rate limit panic. No coding cave sadness. Link in the comments 👇

Gemini just got an update nobody is talking about. And it fixed my messy workflow forever. Most AI chats are dumb. They forget who you are. You upload the same files again and again. It wastes your time. The new Project Notebooks change this. You make one space for a big project. Drop in your PDFs and sheets. Tell it what to do. It remembers everything. Forever. It even links right to NotebookLM. Stop starting from scratch. Build a workspace that actually works.

A man spends 50 years teaching at MIT. He knows his time is running out. So he records one last lecture — everything he knows, distilled into a single hour. He died 5 months later. This is that lecture. The most important hour you'll watch this week. 👇 Bookmark it for later

🚨 This guy literally built an ENTIRE operating system with Claude Code now he’s showing exactly how he did it. he dropped a 2+ hour masterclass and broke down the frameworks behind it, shared a free GitHub repo so you can start immediately: (save this)

Microsoft did it again! Speech AI models have a major limitation. They slice long recordings into tiny chunks, lose track of who's speaking, and forget all context halfway through. This is exactly what Microsoft's VibeVoice solves. It's an open-source family of frontier voice AI models for both speech recognition and speech generation. Here's what it can do: > VibeVoice-ASR processes up to 60 minutes of audio in a single pass. No chunking. It outputs structured transcriptions with who spoke, when they spoke, and what they said. > You can feed it custom hotwords like names, technical jargon, or domain-specific terms. The model uses them to significantly improve accuracy on specialized content. > VibeVoice-TTS generates up to 90 minutes of multi-speaker speech with up to 4 distinct speakers. Natural turn-taking, emotional expression, all in one pass. > VibeVoice-Realtime is a 0.5B streaming TTS model with ~300ms first-audio latency. Small enough to deploy practically anywhere. All of this is powered by continuous speech tokenizers running at just 7.5 Hz. This ultra-low frame rate preserves audio quality while making long sequences computationally feasible. We have shared the link to the GitHub repo in the replies!