Kushagra Yadav

RA @ NYU | MSCS @ NYU | AI/ML Researcher | VLMs · LLMs · GenAI · Multimodal AI | Ex-Pocketpills

[Kushagra Yadav @kushagrayadv]

Aegis — Multiverse Credential Verification Team: @on1onmangoes_63221, @kushagrayadv15, @nalin_41670 Doctor credentialing usually takes weeks. We rebuilt it: snap a badge → credential graph in ~4 seconds. Powered by @googlegemma 4 agent on @Cerebras.
🔗 https://t.co/WlEbh5HP0H

[Andrej Karpathy @karpathy]

This is a new paradigm for interacting with Claude that is significantly more "inline" with all the other human activity org-wide. Once you do all of the under the hood engineering work to make this "just work" (e.g. across tools, integrations, compute environments, memory, security, etc.), Claude basically joins the team in a seamless way - you can talk to it as you would talk to a person and it can help with a very large variety of workloads.

Imo this is the 3rd major redesign of LLM UIUX. The first paradigm was that the LLM is a website you go to, the second was that it is an app you download to your computer. This third one is that it is a self-contained, persistent, asynchronous entity with org-wide tools and context, working alongside teams of humans. It really takes a while to wrap your head around it, but it works and it is awesome.

[Ayaan 🐧 @twtayaan]

Apple just made Docker Desktop optional on Mac.

And it is completely free.

This is apple/container. 26.5k stars no Github.

You can now run Linux containers natively on your Mac without installing Docker Desktop, without a background daemon hogging your RAM, and without paying $21 a month per developer for a commercial license.

Here is what it does:

→ Runs Linux containers as lightweight VMs directly on Apple Silicon using macOS 26 virtualization
→ Fully OCI compatible. Pull any image from Docker Hub, GitHub Container Registry or anywhere else
→ Written in Swift and optimised specifically for Apple Silicon. Faster and lighter than anything Docker Desktop does on Mac
→ Standard container CLI syntax. If you know Docker commands you already know how to use this
→ Push images you build to any standard container registry and run them anywhere

Docker Desktop charges $21 per developer per month for commercial use. Apple's version costs nothing and ships as open source under Apache-2.0.

Microsoft made Docker Desktop optional on Windows with WSL Containers last month.

Apple just did the same on Mac.

Docker is not going anywhere. But the era of paying for a GUI wrapper around containers on your own machine is quietly ending.

Repo here: https://t.co/uFJ867sul6

[Rahul @sairahul1]

Anthropic and OpenAI are both telling engineers to write loops.

Not prompts.
Not agents.
Loops.

That is not a coincidence.

When the two most important AI labs on the planet independently converge on the same pattern — that is a signal worth paying attention to.

Most engineers are still thinking in terms of single calls.

Input → model → output.

The engineers winning in 2026 think in cycles.

Output becomes input. The model evaluates its own work. The loop runs until the result is right.

This is the complete breakdown of what loops are, why they matter, and how to build them ↓

[Pavlo Molchanov @PavloMolchanov]

What if you could take three completely different model families… and distill them into one tiny model? 🤯

📜 Paper: https://t.co/K2iKD4xFvp

MOPD (Multi-Teacher On-Policy Distillation) has become a standard procedure in post-training. We already distill multiple specialized variants of the same model into a single set of weights.
But what if we could go further - and distill models from entirely different families? Turns out, it is possible.

Today we’re releasing a paper on cross-tokenizer distillation - our first steps in this exciting direction. 📄

We distilled Qwen3-4B, Phi-4-Mini, and Llama-3B into Llama-3.2-1B.
MMLU jumped from 32.05 → 46.32 when using multiple teachers. 📈

The team is now working on Nemo-RL integration so the community can try this method in their own settings. Plus, we are scaling experiments up. 🚀

[Suryansh Tiwari @Suryanshti777]

Andrej Karpathy just explained the future of software engineering without directly saying it.

The best AI engineers are no longer “prompting.”

They’re building systems around the agents.

Karpathy’s biggest insight wasn’t:
“Claude can code.”

It was:
LLMs become dramatically better when you force them into disciplined workflows.

That’s why "CLAUDE.md" files are suddenly everywhere.

Not because they’re prompts.

Because they behave like an operating system for the agent.

Karpathy called out the exact problems with AI coding:

- models assume instead of asking
- they overengineer simple tasks
- they hide confusion
- they rewrite unrelated code
- they optimize for completion, not correctness

So developers started encoding rules directly into the workflow:

→ Think before coding
→ Simplicity first
→ Surgical edits only
→ Goal-driven execution

And the results are wild.

People are now running multiple Claude Code agents in parallel like engineering teams:

• one agent researching
• one debugging
• one writing tests
• one optimizing code
• one validating outputs

Not “AI assistance.”

Actual orchestration.

And this part from Karpathy changes everything:

“Don’t tell the model what to do. Give it success criteria and let it loop.”

That is the shift.

From:
“write this function”

To:
“here’s the goal, constraints, tests, and verification system — now iterate until correct.”

The craziest part?

This already feels like a phase shift in engineering.

A lot of developers quietly went from:
80% manual coding → to 80% agent-driven coding in just months.

Not because AI became perfect.

Because the leverage became impossible to ignore.

We’re entering an era where the highest leverage engineers won’t necessarily be the best coders.

They’ll be the people who build the best systems around AI agents.

[tetsuo @tetsuoai]

Neural Network Visualization

[spidey @lochan_twt]

When AI was still a research niche, Yann LeCun was building CNNs for real world text recognition in 1989

[Kushagra Yadav @kushagrayadv]

NeurIPS Best Paper went to Qwen for fixing a core attention issue - not reinventing Transformers. A simple sigmoid gate after SDPA stabilize training and removes attention sink at almost no cost. Proof that deep understanding beats added complexity.

Link: https://t.co/zc9zpKGxAM

[Kushagra Yadav @kushagrayadv]

@IAmPascio Send

[Kushagra Yadav @kushagrayadv]

@Ritik_Singh17 @Shamitha2807 @peakbengaluru @Ritik_Singh17 is that you?😂😂

[Kushagra Yadav @kushagrayadv]

#dtufeesrelaxtation
@msisodia @ArvindKejriwal @PMOIndia @HRDMinistry @GautamGambhir @AtishiAAP @raghav_chadha @SanjayAzadSln @RahulGandhi @RajatSharmaLive @sardesairajdeep @TheLallantop @saurabhtop @nidhiindiatv @ShekharGupta @SanjayAzadSln

[Aishwary Singh @badboyaish]

"We're all in this together", the national slogan at the start of this pandemic when there was an urge for every section of the society to stand together, shoulder to shoulder, but as time has passed, we can clearly see students being left stranded alone ! #dtufeerelaxation

[Kushagra Yadav @kushagrayadv]

Hostel rules should be changed..This is coercion

[Pratyush Harsh @pharsh13]

Dear @ArvindKejriwal Ji and @msisodia Ji Our University (Delhi Technological University) is charging the Mess fee during the lockdown. We pay the entire fee for the University as well as Hostel at the starting of the academic year. Should We only one to suffer ?

[Kushagra Yadav @kushagrayadv]

@VodafoneIN @VodafoneIN I have done the said things many times over but it just doesn't work. The problem is going on from Nov 2019. I had called the customer care many times and visited the store. But it still isn't working.

[Kushagra Yadav @kushagrayadv]

@VodafoneIN I am very dissatisfied with your service. I am not receiving any type of messages on my number and couldn't send messages either. If the problem persists, I suppose I have to switch to other network.