Palash Aggrawal

Computer Science Student, Learning by teaching.

I am into Astronomy, Music, Martial Arts and in general anything :)

[Palash Aggrawal @CosmopalRK]

@thede_plandude Very cool! Open source?

[Feifei Qiu @feifei_qiu]

@elonmusk How FSD handles incoming car for this road

[Alok Gupta @ai_alok]

@system_monarch Use hierarchical spatial indexing like Uber H3 or Google S2.

Precompute restricted regions into cells and do O(1) lookups at runtime instead of expensive polygon check

Built something similar at FamPay handling 10M+ location day with p99 latency <0.5 ms

https://t.co/DJeElZ44d1

[Zeb Evans @DJ_CURFEW]

Today we reduced headcount by 22%. The business is the strongest it's ever been. So I think it's important to be direct about what I'm seeing and why.

First, I made this decision and I own it. I did it because the way to operate at the highest level of productivity is changing, and to win the future, ClickUp needs to change with it.

Second, this wasn't about cutting costs. Most savings from this change will flow directly back into the people who stay. We'll be introducing million-dollar salary bands. If you create outsized impact using AI, you'll be paid outside of traditional bands.

Most importantly, I have the deepest gratitude for those affected. We're doing this from a position of strength specifically so we can take care of people properly. Everyone affected receives a package aimed at honoring their contributions and easing the transition.

I only see two options: wait for this to play out gradually in the market or be honest about what I'm seeing and act proactively.

THE 100X ORGANIZATION
The primary change is that we're restructuring around what I call 100x org. The goal is 100x output. The roles required to build at the highest level are fundamentally different than they were a year ago.

Incremental improvements to existing systems won't get us there. We need new ones. That means creating enough disruption to rebuild rather than iterate on what's already broken.

The common narrative is that AI makes everyone more productive. It doesn't. Many of the workflows of today, if left unchanged, create bottlenecks in AI systems.

These roles will evolve. But waiting for that to happen naturally means falling behind now.

The 100x org is actually heavily dependent on people - infinitely more than today. This is only possible with 10x people that have embraced and adopted new ways of working.

THE BUILDERS, AGENT MANAGERS, AND FRONT-LINERS

— THE BUILDERS: 10X ENGINEERS
I don't think most companies have internalized what's actually happening with AI in engineering. The common narrative is that AI makes all engineers more productive. That may be true in isolation, but at an organization level - that is the farthest thing from reality.

Here's what we've validated recently at ClickUp: the great engineers, the ones who can orchestrate, architect, and review, are becoming 100x engineers. They're not writing code. They're directing agents that write code. The skill is judgment.

AI makes the best engineers wildly more productive, and everyone else using AI slows these engineers down.
Think about it - the bottlenecks are (1) orchestration - telling AI what to do, and (2) reviewing - what AI did. Everything is leapfrogged and no longer needed.
So who do you want orchestrating and reviewing code?

And how do you want your best engineers to spend their time?

If your best engineers are spending time reviewing other people's code, then this is inherently an inefficient bottleneck. These engineers can review their agent's code much faster than reviewing human code.

The new world is about enabling your 10x engineers to become 100x.

The wrong strategy is to push every engineer to use infinite tokens. Companies doing this are celebrating 500% more pull requests. But customer outcomes don't match the volume of code being generated.

I call this the great reckoning of AI coding, and every company will face this soon if not already.

More code is just another bottleneck to the best engineers, and ultimately to your company's impact as well.

— THE BUILDERS: 10X PRODUCT MANAGERS
Product management and design roles are merging.

Designers that have customer focus, become more like product managers.

And product managers that have intuition for UX become more like designers.

The bottleneck of user research is gone. It takes us just one mention of an agent to kickoff research and analyze results.

The bottleneck of product <> design iteration is also gone. The product builder iterates on their own, along with agents and skills that ensure alignment with quality and strategy.

Also controversial today - I believe that the wrong strategy is to have your PMs shipping code - that just introduces another bottleneck that the best engineers will waste their time on.

To be clear, PMs should be coding but they should do this in a playground to iterate, validate, and scope. That code should not go to production.

Everything outside of managing systems, orchestrating AI, and reviewing output becomes a bottleneck.
That's why the other roles that are critical along with these are the systems managers (to reduce bottlenecks) along with a bottleneck you can't replace - customer meeting time.

— THE SYSTEM MANAGERS
Ironically, the people that automate their jobs with AI will always have a job. They become owners of the AI systems - agent managers. We have many examples of these people at ClickUp.

The underlying systems in which we operate are absolutely critical to get right. I think most companies are delusional to think they can iterate on existing systems and compete in this new world.

You must create enough disruption so that old systems are deprecated entirely. If there's any definition for 'AI native' that's what it is.

— THE FRONT-LINERS
In a world that will become saturated with AI communication, the human touch will matter more than anything to customers.

This is a bottleneck that you shouldn't replace - even when agents are high enough quality to do video meetings.

One-on-one meeting time with customers is something that shouldn't be automated. The systems around the meetings should be - so that front-liners spend nearly 100% of their time with customers.

REWARDING 100X IMPACT
In a world where companies are able to do so much more with less, where does that excess money go?
In our case, much of the savings in this new operating model will flow directly back to those that enabled it.

We must reward people that create productivity accordingly. This aligns incentives on both sides. Plus, in a world where your best people create 100x impact, you can't afford to lose them.

You should aim to retain these employees for decades. The context they have and their ability to efficiently orchestrate and review will be nearly impossible to replace.

Compensation bands of today should be thrown out the door. We're introducing $1 million cash/year salary bands with a path available to nearly everyone in the company if they produce 100x impact by creating or managing AI systems.

THE FUTURE
Nearly every company will make changes like these. The ones that do it proactively will define what comes next.

The future is not fewer people. It's different work, new roles, and better rewards for those who embrace it. We're already seeing entirely new roles emerge, like Agent Managers, that didn't exist a year ago.

ClickUp is positioning to lead this shift, not just internally, but for our customers too. I've never been more certain about where we're headed.

[Palash Aggrawal @CosmopalRK]

@sama Mental Evolution of the human race. Somehow we still have the same faults as our ancestors.

[Palash Aggrawal @CosmopalRK]

@zan2434 @eddiejiao_obj @drewocarr How does it manage token costs?

[Zain Shah @zan2434]

Imagine every pixel on your screen, streamed live directly from a model. No HTML, no layout engine, no code. Just exactly what you want to see.

@eddiejiao_obj, @drewocarr and I built a prototype to see how this could actually work, and set out to make it real. We're calling it Flipbook. (1/5)

[luthira @luthiraabeykoon]

We implemented @karpathy 's MicroGPT fully on FPGA fabric.

No GPU.
No PyTorch.
No CPU inference loop.

Just a transformer burned into hardware, generating 50,000+ tokens/sec.

The model is small, but the idea is not: inference does not have to live only in software 👇

[Palash Aggrawal @CosmopalRK]

@LunarResearcher @grok explain this in more detail

[Jared Friedman @snowmaker]

What I told 2,000 future founders in Bengaluru today:

1/ We believe we are at the start of a second wave of Indian companies that will build world-class AI native products for the global market. Emergent and Giga are the model of the future.

2/ Just because a space seems crowded doesn't mean it's too late. Zepto, Emergent, Giga - none were first movers. Second mover advantage is real.

3/ In fact, a good formula for finding startup ideas is to look at ideas that are showing some promise and just execute them better. Execution is everything: if you're an exceptional engineer, and you can build and move faster than your competitors, you'll win.

4/ There is every reason to believe Indian teams can beat US teams building global products. The level of engineering talent here is on a whole different level, and that's the key input.

5/ In the AI era, the best founders are the ones building at the edge of what's technically possible. You need to be experimenting wth the latest models, the latest open source projects.

6/ Stay in the flow of information. Watch the right podcasts, follow the right people on X. With AI changing this fast, you need to know what the smartest builders are thinking.

7/ Most of the best startups don't come from someone explicitly trying to start a company. They start from someone building a project just for fun, or tinkering with a new technology because they are curious. India needs more of this "tinkering" culture - this is how you have novel ideas when technology is shifting quickly.

8/ Founders are getting younger. Aadit was 18 when he started Zepto. The Giga founders were 20 when they came to SF. Young people who can learn very fast have the advantage right now.

9/ The best founders are pushing AI coding to the max. You can now write 20K lines of code / day. One person can do the work that just a year ago would take a 100 person team. The best builders are taking advantage and building at Garry Tan speeds.

[Tech with Mak @techNmak]

Andrej Karpathy wrote something that every Claude Code user has felt but couldn't articulate.

Three quotes. Read them slowly.

"The models make wrong assumptions on your behalf and just run along with them without checking. They don't manage their confusion, don't seek clarifications, don't surface inconsistencies, don't present tradeoffs, don't push back when they should."

"They really like to overcomplicate code and APIs, bloat abstractions, don't clean up dead code... implement a bloated construction over 1000 lines when 100 would do."

"They still sometimes change/remove comments and code they don't sufficiently understand as side effects, even if orthogonal to the task."

You've seen all three. Probably this week.

Someone turned these three observations into a single CLAUDE[.]md file. Four principles, one install, directly addresses each quote:

1./ Think before coding
Don't assume. Don't hide confusion. State ambiguity explicitly. Present multiple interpretations rather than silently picking one. Push back if a simpler approach exists. Stop and ask rather than guess.

2./ Simplicity first
No features beyond what was asked. No abstractions for single-use code. No "flexibility" that wasn't requested. No error handling for impossible scenarios. The test: would a senior engineer say this is overcomplicated? If yes, rewrite it.

3./ Surgical changes
Don't "improve" adjacent code. Don't refactor things that aren't broken. Match the existing style even if you'd do it differently. If you notice unrelated dead code, mention it, don't delete it. Every changed line should trace directly to the request.

4./ Goal-driven execution
Transform "fix the bug" into "write a test that reproduces it, then make it pass." Transform "add validation" into "write tests for invalid inputs, then make them pass." Give it success criteria and watch it loop until done.

This last one is Karpathy's key insight captured directly: "LLMs are exceptionally good at looping until they meet specific goals... Don't tell it what to do, give it success criteria and watch it go."

It's a single file. Drop it into any project.

[Pika @pika_labs]

Conversations tend to go better with a face and a voice. That’s why we’re thrilled to release the beta version of the first video chat skill for ANY agent, powered by our new real-time model, PikaStream1.0.

The skill preserves memory and personality, and enables real-time adaptability. And if you use it with your Pika AI Self, they’ll be able to execute agentic tasks during the call 💅

[Andrej Karpathy @karpathy]

LLM Knowledge Bases

Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So:

Data ingest:
I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them.

IDE:
I use Obsidian as the IDE "frontend" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides).

Q&A:
Where things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale.

Output:
Instead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up "filing" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always "add up" in the knowledge base.

Linting:
I've run some LLM "health checks" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into.

Extra tools:
I find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries.

Further explorations:
As the repo grows, the natural desire is to also think about synthetic data generation + finetuning to have your LLM "know" the data in its weights instead of just context windows.

TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.

[Palash Aggrawal @CosmopalRK]

@bcherny Definitely the remote control and Mobile access. Although I still keep getting connection drops… I intend to continue work when I step out, but after a couple hours, the mobile app stops responding and I have to reconnect rc when I get back home.

[Jaynit @jaynitx]

In 2019, MIT professor Patrick Winston gave a legendary 1-hour lecture called “How to Speak.”

It has 18M+ views for a reason.

His frameworks:
• Your ideas are like your children
• The 5-minute rule for job talks
• Why jokes fail at the start

15 lessons on communication:

[Eugen @EugenAlpeza]

We’re out of stealth.

Today, we’re also announcing our Series A led by @sequoia , @8vc , and @A_StarVC , bringing our total funding to $30M+.

Every enterprise needs to teach their AI how to do work. We build agents that reverse engineer enterprise processes, then run them.

Read about the future of learning in the enterprise: https://t.co/ONBjA7MEEJ

[Yousif Astarabadi @yousifa]

https://t.co/Qmta9nro9I

[Elvis @elvissun]

https://t.co/DotZ3V6XhJ

[Palash Aggrawal @CosmopalRK]

@gunsnrosesgirl3 Binge Watching

[Palash Aggrawal @CosmopalRK]

@thefactitorium @gunsnrosesgirl3 Very true. But mastery in anything is rewarding, and that comes from hustling.