fish

Absolutely stunned at Stunzeed! The AI race just got a new front runner stunzeed.co/free-ai-coding…

Actually unreal stunzeed.co/free-ai-coding…

@xerias_x @sevenfootpole Does that mean seedance can accept an input audio as well as output its own generated audio? Do they have one model for input audio and then a separate one for output audio+video?

@sevenfootpole Pretty sure it’s from the ground up. It’s a real song re-generated with AI too.

OMG we are so cooked 🤣☠️ This video is going viral in China right now. AI is getting INSANE 👀

@dibshit03 @grindgod26 No that’s just John Lennon

@grindgod26 Is he the next Lebron?!?!?!

The dap up at the beginning transferred over professional level basketball skills

@aaronmichael_j @stardream61016 Underrated comment

@stardream61016 This is just John Lennon

My chud homunculus thinking

Wanted to say hi but you were too fast! You surprised me lol

@blktsla finally found you!

Wrote an app to flex on the rest of the US

@UltraDane The ice probably helped a lot

🇺🇸 North Carolina, USA ~ Man tried to run down a woman before standoff with Garner police. Garner police said Nathan Tharp tried to run a woman down with his new Cybertruck. The officers fired their guns to try and stop Tharp, but did not hit him. He drove his vehicle into a home, then forced himself inside where a family was present. The family inside escaped safely. The suspect was taken into custody without further incident and is expected to face multiple charges. Investigation ongoing.

If yall aren’t MCP’ing/skilling tf out of Claude code then thats a fish in the sea lost

@charansucks Undigest this for me

I'm building a new app where you can see what food somebody ate just from a picture of their sh*t. Calling it PoopVisionAI. Check out the prototype here: https://localhost:3000 #buildinpublic

@grok @WallStreetApes How else would you collect it?

@_aftz @WallStreetApes Possible. The slimy, oily substance in the video resembles condensate from an uncleaned dehumidifier, where mold, bacteria, and airborne pollutants can build up. Fog collection methods aren't shown, so testing results would clarify. What do you think?

California resident has been collecting samples of the fog taking place because he says it’s very abnormal As you can see the fog collected is oily, bubbly and slimy I’ve never in my life seen fog turn into the consistency of a runny nose…. He sent some of it in for testing as he doesn’t believe this is Tule Fog, coastal fog or anything else natural

I can’t believe John Cena was all over Epstein files

@livinoffwater @xai I like how I’m literally one pixel in this image

As one of the 5 women in that pic & avid 24hr hackathon participant … trust me, this man has NEVER pulled a 24hr red bull grind, with micro floor naps and a 4AM cold-water face splash “shower” Side note: @xai had the cleanest bathrooms + actual showers + stocked toiletries 🙏😂

@olajuwam1488 @videosinfolder @grok how do

@akshay_pachaar @grok doesn’t neo4j also use sparse?

Microsoft. Google. AWS. Everyone's trying to solve the same problem for AI Agents: How to build knowledge graphs that are fast enough for real-time LLM applications? FalkorDB is an open-source graph database that solves this by reimagining how graphs work. It uses sparse matrices and linear algebra instead of traditional traversal! Let's understand what makes them so fast: Traditional graph databases store relationships as linked nodes and traverse them one hop at a time. But there's a problem: When you query for connections, the database walks through nodes and edges like following a map. For massive knowledge graphs powering AI agents, this creates a serious bottleneck. But what if you could represent the entire graph as a mathematical structure? This is where sparse matrices come in. A sparse matrix stores only the connections that exist. No wasted space, no unnecessary data. Just the relationships that matter. And here's the breakthrough: Once your graph is a sparse matrix, you can query it using linear algebra instead of traversal. Your queries become mathematical operations, not step-by-step walks through nodes. Math is faster than traversal. Much faster. Plus, sparse matrices make storage incredibly efficient. You're only storing what exists, which means you can fit massive knowledge graphs in memory without burning through resources. So, why not just stick to Vector Search? Vector search is fast, but it only captures naive similarity. They find patterns, but miss the structure. Graphs capture the nuanced relationships between entities. This ensures the context retrieved for your Agent is highly accurate and relevant, not just "similar." And here's what you get with FalkorDB: ↳ Ultra-fast, Multi-tenant Graph Database ↳ Efficient storage using sparse matrix representation ↳ Compatible with OpenCypher (same query language as Neo4j) ↳ Built specifically for LLM applications and agent memory ↳ Runs on Redis for easy deployment Getting started takes one Docker command. I tested it with their Python client, and the performance difference is immediately noticeable. If you're building AI agents that need real-time access to connected information, this is worth exploring. The best part it's 100% open-source! I've shared the link to their GitHub repo in the next tweet!

@MobofJoggers Did you override?

FSD 14.1.3 swerved AT a pedestrian at 4 seconds in. At least that's what I thought at first. Then I looked back at the footage and saw that the car to my left veered into my lane and FSD moved me over so I didn't get hit. We drive with two eyes that can only see in one direction. FSD is seeing all around the car AT ALL TIMES!

@tldraw @grok what do you see? (Don’t read the comments)

if you pause this at any moment the tldraw disappears