NILAY1556

@het_bhalani Kaha hen bata bhai...me bhi aa raha hu, yaha kuch nahi rakha

Grass?? Decided to touch sand today!

Hermes Agent now has multi-agent via the Kanban, new in v0.12.0. Agents claim tasks from a board, work in parallel, and hand off when blocked. You watch progress and unblock from one easy view instead of juggling terminals. We asked it to plan and make this video about itself:

@codetalker07 @Google Lfg man!!

this summer, i'll be spending my time at @Google as a PhD SWE intern, working on efficient inference. super excited to learn from the best!

@het_bhalani Badhu j sara vala thai jase bhai

I have lost 4 games in a row in chess🙂

We added @karpathy -inspired coding rules from @jiayuan_jy to AGENTS.md and ran 40 @openclaw PRs through three coding agents. The result: Code quality was basically unchanged, but the agents got there with less work. Fewer tool calls, lower time and cost.

Meet Human Operator from MIT Media Lab: a wearable that lets AI temporarily take control of your hand using electrical muscle stimulation. Watch it crush piano, draw perfectly, and mix cocktails like a pro — all from a simple voice command. “I gave an AI a body.” This isn’t sci-fi. This is tomorrow. #HumanOperator #MITMediaLab

@het_bhalani For that ai had "skills"

I think the biggest skill today is debugging the AI written code!

Launching MemeHub! Backed by Your MoM > Closed Source > Free forever > Available at meme.ramx.in

made this video on how to win humanity's last hackathon. remember, this hackathon is on context engineering, not code. so you need to build agent scaffolds that can solve problems themselves/ It's a async competition to write optimized kernels. Why? Because faster kernels improve performance on local models. How? Sign up via the app and you'll get notified. What? you'll need to build agent scaffolds with skills, mcps, hooks, and agents. They'll need to research and build optimize kernels, end-to-end. When? kick-off May 15th. Sign up here: hf-learn.short.gy/nvB8JD Check out this video: youtube.com/watch?v=xRFuPk…

@MrBeast Like one

If this tweet has exactly 1 like in 24 hours I’ll give that person $1,000,000

@het_bhalani Which anime should I watch next

i have 100 GiB of movis in my laptop, want recommendations?

with Mira, AI can now live on your face. capture every conversation. create the most personalized form of AI ever. order now.

@AndrewYNg I wonder why sir posting manually the same post ? 2 days ago deeplearning post this course, or is it for to reach more ppl ( like the repost technic ) ?

How we prompt AI is very different in 2026 than 2022 when ChatGPT came out. I'm teaching a new course, AI Prompting for Everyone, to help you become an AI power user — whatever your current skill level. It covers skills that apply across ChatGPT, Gemini, Claude, and other AI tools. How to use deep research mode for well-researched reports on complex questions. How to give AI the right context, including more documents and images than most people realize you can provide. When to ask AI to think hard for several minutes on important decisions like what car to buy, what to study, or what job to take. And how to use AI to generate images, analyze data, and build simple games and websites. I also cover intuitions about how these models work under the hood, so you know when to trust an answer and when not to. Along the way, you'll see flying squirrels, a creativity test, some of my old family photos, and fireworks. Join me at deeplearning.ai/courses/ai-pro…

@NousResearch @lmstudio Waiting for vLLM

LM Studio is the most popular way to run open-source LLMs on your own hardware. Your Hermes Agent now runs natively on @lmstudio: auto-discovering your models, loading them on demand with the right context size, and using the right reasoning level for each model.

Offline vibe coding with Gemma 4. This open-source Electron app runs entirely on your Mac via Apple's MLX framework. No Wi-Fi required.

ReLU vs Leaky ReLU 👉 byhand.ai/qRHNCA = ReLU = ReLU is the default activation in modern deep learning — cheap to compute, and stable enough to train networks hundreds of layers deep. To see what it does, picture five boba tea shops on the same block — 𝚊, 𝚋, 𝚌, 𝚍, 𝚎 — each running their own books. Each value is a shop's monthly profit — receipts minus rent, ingredients, and wages. When profit is positive, the shop stays open and the owner pockets every dollar. When profit turns negative, the shop runs out of cash and shutters — the lights go off, the books are wiped to zero. ReLU is exactly that rule, applied one shop at a time. Read the diagram left to right. The first column is the raw value x — each shop's profit at month's end. The second column is the gate: 1 if the shop is open (x > 0), 0 if it has shuttered. The last column is the ReLU output: open shops pass their profit through untouched, while shuttered ones are zeroed out. Five rows means five parallel shops on the same block, each evaluated independently. That's why ReLU is called an element-wise activation: every neuron decides its own fate. = LeakyRelu = Plain ReLU wipes negative values to zero — clean, but a shop that shutters can never recover, since both its output and its gradient stay pinned at zero. This is the dying ReLU problem, and in deep networks it can quietly kill a meaningful fraction of the units. Leaky ReLU is the one-line fix: instead of shuttering, the shop files for Chapter 11 protection and keeps the lights on at reduced capacity. Its debt is restructured down to a fraction α (typically 0.1) — the rest is forgiven, and the shop is wounded, not killed. A small negative signal still flows through, so the gradient survives, and the shop can crawl back to life if a TikTok goes viral. Read the diagram left to right. The first column is the raw value x — each shop's profit at month's end. The second column is the leakage α — the fraction of the loss held over after restructuring (default 0.1, editable). The third column is the gate: 1 for shops still in the black, α for those operating under bankruptcy protection. The last column is the Leaky ReLU output: y = x · gate. Profitable shops pass through untouched; struggling ones shrink by a factor of α but still carry a sign. Five rows means five parallel shops, each evaluated independently. Like ReLU, this is an element-wise activation: every neuron's fate is decided on its own merits. #aibyhahd

@djipowerglobal Me to my luck "I love the way you lie"

Labor Day is around the corner. We’re giving away ONE Osmo Pocket 4! 🎁 Ready to level up your travel content? Enter now! How to enter: Follow @djipowerglobal Like, comment, and repost Ends May 14 Winner announced May 15 (EST) Open worldwide Fingers crossed!

Most engineering orgs have adopted AI coding tools. Far fewer have changed how they build software. There's a difference between adding AI to your workflow and rebuilding the workflow around AI. We're hosting a session that discusses an engineering team that transformed their SDLC, and sharing exactly what it took. If you're leading an engineering org and trying to move from experiment to operating model change, this one's worth your time. Register here for our session on May 1 at 10:30 AM PT: watch.getcontrast.io/register/augme…

Just fly.