Rohkaseana Saraan @caseacasea88

o4-mini-high Prompt: "Simulate a galaxy using thousands of small particles orbiting a center point. Add simple mouse controls to rotate the view. Use gradient colors, spiral motion, and star-like glows for that wow factor. In one html file"

5 5 123 22K 67

View Details

Rohkaseana Saraan @caseacasea88

a year ago

@Tabby_Fashion I want it @Tabby_Fashion

0 0 0 4 0

View Details

Rohkaseana Saraan @caseacasea88

a year ago

@hasantoxr Grok

0 0 0 1 0

View Details

Rohkaseana Saraan @caseacasea88

a year ago

Grok

Hasan Toor @hasantoxr

a year ago

Grok 3 is a powerful AI Tool. But most people don’t know the best ways to use it. That's why I build this Ultimate Guide to Master Grok. • 10+ Chapters • 100+ Prompts • 10+ Curated Cheat Sheets • Save 700+ hours on research Just: • Reply "Grok" I'll DM you the guide

2K 189 1K 271K 1K

0 0 0 18 0

View Details

Rohkaseana Saraan @caseacasea88

a year ago

@Jacobsklug @lovable Build

0 0 1 2 0

View Details

PicoCreator - AI builder @ ✈️🌉 @picocreator

a year ago

I am infra guy as much as I am an AI guy This is one hell of a flex bigger then the previous You AI folks have no idea how much blood sweat and tears have been poured into making reliable distributed storage, at a fraction of these performance numbers x.com/deepseek_ai/st…

DeepSeek @deepseek_ai

a year ago

🚀 Day 5 of #OpenSourceWeek: 3FS, Thruster for All DeepSeek Data Access Fire-Flyer File System (3FS) - a parallel file system that utilizes the full bandwidth of modern SSDs and RDMA networks. ⚡ 6.6 TiB/s aggregate read throughput in a 180-node cluster ⚡ 3.66 TiB/min

523 1K 10K 3.2M 3K

13 157 2K 207K 670

View Details

Cormac @cormachayden_

a year ago

We've entered single-player founder mode - @testimonialto $1.5m arr - @quittr_app $3m arr - @levelsio $3m arr - @chatbase_co $3m arr - @tdinh_me $1.2m arr - @carrd $2m arr - @blakeandersonw $18m arr - @dannypostma $3m arr - @seedoilscout $1m arr - @marclou $2m arr

86 238 3K 453K 5K

View Details

Philipp Schmid @_philschmid

a year ago

The AI-Co Scientist paper dropped! The @GoogleAI -Co Scientist is a Multi-Agent System build with @GoogleDeepMind Gemini 2.0 designed to generate scientific hypotheses through generate, debate, and evolve approach combining specialized agents and reasoning. The 80 page long paper includes prompts, example outputs and full reports generated by the AI-Co Scientist. 👀 Agents: > Supervisor Agent: Orchestrates the research process, assigns tasks to agents, allocates resources to other agents based on the research plan. > Generation Agent: Creates initial research hypotheses by exploring literature, simulated debates, and identifies testable assumptions. > Reflection Agent: Reviews hypotheses (peer review), assesses correctness, quality, novelty, and potential to explain existing observations, with different review types. > Ranking Agent: Creates pairwise comparisons of hypotheses (tournament-style), using simulated debates to create a Elo rating > Evolution Agent: Refines best hypotheses by grounding them in literature, improving coherence/feasibility, combining ideas and exploring "out-of-the-box" thinking. > Proximity Agent: Groups similar hypotheses to optimize exploration diversity. > Meta-review Agent: Synthesizes insights from all reviews, identifies patterns, optimizes other agents' performance, and creates report Implementation: 1️⃣ Scientist provides a research goal, e.g., "Find AML drug candidates". 2️⃣ Supervisor Agent parses the research goal and creates a structured research plan. 3️⃣ Generation Agent explores literature and engages in simulated debates to generate initial hypotheses. 4️⃣ Reflection Agent identifies weaknesses via 6 review types (e.g., deep verification). 5️⃣ Ranking Agent creates pairwise Elo tournaments through AI debates. 6️⃣ Evolution Agent refines the top-ranked hypotheses. 7️⃣ Meta-review Agent generates overview report and shares it with the Scientist. 8️⃣ Scientist provides feedback, adds hypotheses for the next iteration. Insights: 🧠 Powered by Google Deepmind Gemini 2.0 models 💡 Using Thinking/Reasoning Model boosted hypothesis quality by 300+ Elo points 📈 Specialized agents, mimicking the scientific method, imporved hypothesis generation 🔄 Self-improving loop: Meta-review feedback increased hypothesis novelty scores by 27% 👥 Expert-in-the-loop design allows scientists to refine goals and provide feedback 📝 Design of the prompts are a significant factor for performance 👀 Paper includes prompts, example outputs and full reports generated 🦠 Rediscovered (in 2 days) a bacterial gene transfer mechanism (took 10 years of manual) -> not sure thats a fair comparison

13 134 578 43K 481

View Details

Ben Dower @nobody_qwert

a year ago

🚀Easy 3D models in HTML games 1. Download some free 3D animated model. 2. Open in blender and export it as glTF 2.0 .glb file. 3. Prompt AI model like Grok 3 or Sonnett 3.7 for loader. 👉Sample loader HTML implementation chat: x.com/i/grok/share/B… - Thread 🧵

3 4 9 2K 15

View Details

@

a year ago

25 years after this speech, Steve Jobs made this big idea a reality. On July 10, 2008, Apple, Inc launched the App Store, allowing developers to share their creations with anyone who had an iPhone. Indeed, big ideas are always worth exploring. So dream consistently, and close the gap between ideas and execution. ___________________ #appstore #apple @Apple #history #stevejobs #futureofwork #entrepreneur #motivation #success #inspiration #iphone #tech #mwc25 #mwc #video