Ruu

Finally 👊

A 35-year-old marketer from Hong Kong quit his job and got deeply into AI. Using Claude, he made $360,000 in just one month. He built a perfect BTC price simulation engine with MiroFish. Claude as algorithm’s brain + MiroFish simulation engine allowed him to earn $5,000-$15,000 in profit per trade. His wallet: @marketing101?via=cvxv666" target="_blank" rel="nofollow noopener">polymarket.com/@marketing101?… He left a funny easter egg about his previous profession in his Polymarket nickname - he called himself Marketing101. His algorithm instantly detects any mispricing in crypto markets and enters trade immediately. $366k all-time profit. Constantly fading the crowd because his simulation reads the market better than everyone else. He’s using closed order book data + private OTC desks. Already elite alpha. Then the real magic happens: 10,000 simulation cycles of how the market will react. This isn’t "guessing where the chart will go" This is engineered money. Pure fusion of AI + MiroFish + insane math on exclusive data. Want to learn how to build something like this? Save the post and read the article. If you don't want to miss his next success trade, starting copy every one of his trades right now using this TG bot: @cvxv666" target="_blank" rel="nofollow noopener">kreo.app/@cvxv666

New Gemini looks SICK!!!

Super excited that @cocoindex_io made to Python trending! Built on Rust Core, CocoIndex provides ultra performant python-native experience that turns codebases, PDFs, Slack, inboxes, and videos into a continuously updated index your LLM app can reason over. CocoIndex has been showing up on Rust trending quite a few times in the past year. and with V1 launch, we have added more connectors and examples and made python takes bigger half of the repo. Stay tuned as we ship Rust SDK and more examples, and we may go back to Rust trending again later ;)

wkwk nice meme

Demis Hassabis says he plays chess with Gemini to trace the model's chain-of-thought. As a former chess prodigy, he can tell when the model starts reasoning itself into trouble. Sometimes it sees a blunder, searches for something better, then plays the blunder anyway. That’s what jagged intelligence looks like.

Python made AI accessible. Rust can make parts of AI understandable. That’s the bet behind Category Theory for Tiny ML in Rust. We’re building tiny ML systems from first principles using: Rust types typed transformations composition training loops category theory as an engineering tool Not abstraction cosplay. Executable structure. Working draft. Public feedback welcome.

Local-first AI LaTeX editor for researchers github.com/EvolvingLMMs-L…

What if Microsoft designed YouTube?

What is GRPO? Group Relative Policy Optimization is a reinforcement learning method that fine-tunes LLMs for math and reasoning tasks using deterministic reward functions, eliminating the need for labeled data. Here's a brief overview of GRPO before we jump into code:

🎉Introducing PyFlue: The Python-Native Agent Harness Framework.🧰 💡Flue for Python: Fred K. Schott @FredKSchott CEO of HTML has launched Flue: The Agent Harness Framework for TypeScript. It brings programmable harness right into your agents rather than DIY plumbing. Python ecosystem already has 🦾 powerful AI/ML tools and frameworks and research initiatives but most frameworks asked users to build your own harness. Superagentic AI bringing this concept of Flue to Python 🐍 ecosystem. Here is PyFlue even even better 🤖 Agent = Model 💻 + Harness 🧰 + Memory 🧠 Almost all the feature of Flue plugged with @LangChain Deepagents harness built by @hwchase17 and team @Vtrivedy10 @sydneyrunkle and more coming soon. 👉 Stop building agent loops, start using a harness. 💻 Try PyFlue Now : super-agentic.ai/pyflue ⭐️ GitHub: github.com/SuperagenticAI… 📚Docs: superagenticai.github.io/pyflue/ 📙 Blog Post: super-agentic.ai/resources/supe… #HarnessEngineering #AgentHarnesses

Your Everyday Tools Desktop v1.2.2 sudah dirilis🎉 Update dari v1.1.0: - 10+ tools baru: Fill PDF Form, Redact PDF, dan lainnya - Installer lebih ringan, bisa custom install - Auto-update langsung dari app Download di 👇 github.com/rachmad-jenss/… cc: kak @listyantidewi

Anthropic pays $750,000+ a year for engineers who can build LLM architectures from scratch. Stanford taught the entire thing in 1 hour lecture & released it for free. Bookmark & watch this today before someone takes it down.

Fine-tuning increases hallucinations New research shows SFT causes factual errors by interfering with pre-trained knowledge. The authors propose self-distillation to learn new facts without forgetting, plus selective parameter freezing to reduce hallucinations while preserving performance.

Context may be the most under-engineered layer in AI coding today. In this keynote, @patrickdebois, argues that if agents are driven by prompts, rules, and memory, then context deserves the same rigor we already give code. youtube.com/watch?v=bSG9wU…

Here is a 2nd batch of April architecture drops. What a month! - Ant Ling 2.6 1T - Minimax M2.7 - Xiaomi MiMo V2.5 - Poolside Laguna XS.2 - Tencent Hy3-preview - IBM Granite 4.1

27x faster Attention Residuals!!! 🚀 We implemented Block AttnRes as a pip-installable package. !pip install flash-attn-res No annoying kernel nonsense. No compile/autograd plumbing. Call it like a regular PyTorch op. It just works. Methodology: 🔹 fused triton kernels 🔹 batched attention over residual blocks 🔹 online-softmax merge 🔹 flash attention-style split-KV reduction Thanks @LLMenjoyer and @cartesia for the support and guidance✌️

Uda biasa coba ChatGPT, Claude, Perplexity, Gemini kan? Go try Amazon Quick Suite. Lay out jawabannya lebih structured dan isi-nya lebih contextual. Dia ga harus download di PC. Bisa web-based. Sebelumnya gw pake ini cuma internally di kantor. Skrg ternyata uda dipublish bt khalayak umum! 🔥

ini gak ada kah? #zonauang #zonajajan

「ベクトルDBを使わないRAG。全てのナレッジを階層化する手法」が有益。 ベクトル検索の精度に悩むチーム向けに、ナレッジを階層化する新しいRAGアーキテクチャを提案。コストもベクトルDB依存も下げられる、現場で即試したくなる手法。 こちら→ zenn.dev/knowledgesense…

Congratulations to the @DeepgramAI team on this integration of seamless multi-lingual support into their flagship Flux transcription model. Many voice agent use cases require that the agent understand and speak multiple languages. To support this, we often build complex pipelines with components that perform language detection and language switching. What we really want is for the models we use to just naturally understand multiple languages! Flux is fast, with integrated turn detection, and is the speech-to-text model in a very large number of production voice agents. This new multi-lingual support makes it even more useful.