DontBeAn85RetailIQ ⏩
@nihilhackspace
Don't Tool Second, LiferSystemize
You might like
Michelle Trachtenberg received a liver transplant shortly before her death at 39. one of her favorite foods was spinach and cheese pasta. Very high in vitamin A. she recently underwent a liver transplant for a failing liver that began somewhere around 2024.
❤️
This is just so insane to have on an airplane. Please make it a law that all commercial flights must have starlink. Congrats @elonmusk
Poverty is an engineering problem
I see poverty as more of an engineering problem than an unsolvable social issue. With Grok and Optimus, we could solve the labor shortage, drive costs to near zero, and create a future where poverty is statistically irrelevant. The scale of whats coming over the next decade is…
Dr. Fei-Fei Li on LLMs vs spatial intelligence: “Language is fundamentally a purely generated signal… you don’t go out in nature and there’s words written in the sky for you.” “There's no language out there. You don't go out in nature and there's words written in the sky for…
Introducing Marble by World Labs: a foundation for a spatially intelligent future. Create your world at marble.worldlabs.ai
Claude Skills is the best feature I’ve ever used. Kudos to @AnthropicAI team.
100% browser-based "vibe coding" with Claude Code 1. Create a blank GitHub repo 2. Connect it in Claude Code (web or mobile) 3. Link the repo to @Netlify or @vercel for auto-deployment 4. Ask Claude Code to build your app 5. Create a Pull Request (don’t merge) — this triggers a…
Today I’m launching Swipe -- a new way to steer image models. The idea is simple – start with a prompt, swipe left / right to steer the model towards what you’re thinking of.
The best math you can learn is how to calculate the future cost of current decisions.
I have to start closing the entropy loops or I will always feel tired. Entropy loops need to be closed.
LLMs are injective and invertible. In our new paper, we show that different prompts always map to different embeddings, and this property can be used to recover input tokens from individual embeddings in latent space. (1/6)
CLAUDE IS SO MUCH BETTER WHEN YOU USE MCP Both Claude Sonnet and Opus are Insanely smart Agents. But they can't read your mind. You need to Give it Context... (MCP = model CONTEXT protocol) Here is an example... Then a tutorial on how to give Claude access to MCP tools…
Talking to @pmarca can be strange because he's constantly next-token-predicting *your* chain-of-thought. I can just say "remember that essay...," and he'll just pull up the 1989 essay I was trying to remember Also, why I'm bearish on a true AGI breakthrough in the near term:
if you wanna gain an edge, your LLM must understand your business better than you do...
Habits that have a high rate of return in life: - sleeping 8+ hours each day - lifting weights 3x week - going for a walk each day - saving at least 10 percent of your income - reading every day - drinking more water and less of everything else - leaving your phone in another…
Claude Code Skills are brilliantly token-efficient. Save this post, you'll want it when setting up and using Claude Code. They auto-load only when needed with progressive disclosure and unlimited references. You only pay for what you actually use. Here's a quick comparison…
Andrej Karpathy says today's agents aren't ready to work like real coworkers or interns They lack intelligence, can't use computers, aren't multimodal, lack continual learning, and forget what you tell them Fixing these gaps will take about a decade
Claude Skills are awesome, maybe a bigger deal than MCP simonwillison.net/2025/Oct/16/cl…
95 ---> 99% mAP is a chasm, but I like your chutzpah.
This cybersecurity expert explains how hackers are using Gemini by writing hidden instructions into images
United States Trends
- 1. Klay 23.2K posts
- 2. Good Sunday 53K posts
- 3. McLaren 92.7K posts
- 4. Lando 131K posts
- 5. #FelizCumpleañosNico 2,614 posts
- 6. #FelizCumpleañosPresidente 2,572 posts
- 7. #AEWFullGear 72K posts
- 8. Ja Morant 10.4K posts
- 9. #LasVegasGP 223K posts
- 10. Oscar 122K posts
- 11. Piastri 68.2K posts
- 12. Verstappen 99.7K posts
- 13. Gambino 3,129 posts
- 14. LAFC 16.5K posts
- 15. Kimi 53.8K posts
- 16. Hangman 10.5K posts
- 17. Samoa Joe 5,350 posts
- 18. Tottenham 36.9K posts
- 19. Swerve 6,680 posts
- 20. South Asia 36.9K posts
Something went wrong.
Something went wrong.