Aravind Putrevu

Team CodeRabbit is at AI Engineer Hackathon SF!

Can anyone tell me why all the HR platforms are old and have irrating UIs.

Why there is a no Linear or Figma version to these?

😭

Excited to be at SF this week and starting the week with a bang.

Join me at SF AI Dev Tools meetup this monday evening 5 pm

link in thread

A very well-written article on an important topic - React!

New episode of This is Tech Talks is live, this time we deep dive into Gen AI with our guest @aravindputrevu , go ahead and listen to the episode as we talk about everything you need to know about Gen AI with our hosts @SonuKapoor1978 and myself YT: https://youtu.be/VFlik7TiNE0

New episode of This is Tech Talks is live, this time we deep dive into Gen AI with our guest @aravindputrevu , go ahead and listen to the episode as we talk about everything you need to know about Gen AI with our hosts @SonuKapoor1978 and myself

YT: youtu.be/VFlik7TiNE0

Writing will be more important in the coming days, which means you need to develop clear thinking, too.

I made two AI Coding agents talk to each other - Devin for creating a PR and CodeRabbit to review them.

All from Slack - on the weekend!

Something new this morning!

Most Developers are naturally introverted, except a few who write personal blogs and post on hacker news :P

PR Reviews is a situation where they have to speak and explain, but it is also a harder soft skill.

Yes, all the team fit rounds, HR rounds, those technical problem explanation questions (where they ask a silly question and we fail, but we get moved to the next round)

I agree that PR Review is an educational experience. Only when it is not used for blocking or doing silly politics (like teaching an unnecessary lesson on the history of programming)
It should be fun.

Coming to this question about testing in the interview - you are being tested.

Surprised?

I have this feeling: Products lose traction when they stop innovating and stop working on the mission that they started with.

- Organize the world's information: Google
- Make work life simpler, more pleasant and more productive - Slack

It looks like they are gunning down on Notion, the Atlassian of the world, rather than listening to users.

Let us take a look at Slack. Coming from IRC and the mailing list world, I instantly loved it. Infact, I built a massive community on Slack for Elasticsearch, despite knowing it is a paid-only tool.

Today, with AI, Slack search is poor, and the AI summarization is terrible, let alone workflows.

I hate it when good products suck and slowly become obsolete.

I have seen this happen with Databases and Dev Tools.

And, now, with AI, the SaaS apps, which were cool yesterday, are lagging behind.

They think they know, while they might not. It is like an infant trying to catch the orange-ish charcoal, thinking it is a color that doesn't harm.

I guess the emergent behaviors with LLMs (ofc configured by LLM providers) are making and executing decisions.

---

This is where we and AGI-ready LLMs probably diverge.

I want something else, and it would probably have been good if it had stopped by Step#1.

I asked Claude 3.7 + GitHub MCP to do one thing. Very specifically, one thing.

It did 3. I understand the line of thought, and it uses the chat context to make decisions autonomously. But that is not what I want it to do!

I used DeepResearch 100 times last month 🙈

Why a lot many don't understand how cool is DeepResearch.

Discovered it first on Google Gemini.. never stopped using it after introduced on ChatGPT.

I got the wifi pass on the flight to AMS from SF (Thanks KLM)

However, it only worked until I hit - npm install 😂

not a joke!

What is stopping Google from making GDrive search-centric? I one-shotted this. I would love to have a notebookLM-ish experience on drive.

Because I was not able to play, I changed the rules. Make fresh challenges.

This is getting more funnier, and I am now getting new thoughts.

I just realized today that I have access to SORA along with ChatGPT Pro

That being said, LLMs, too, lose their charm if the extra examples don't give me results. For example, several times, I try to generate something that fails miserably. After three attempts, I turn to human help!

For an average human being, ramping up on a task might have more questions, and examples might not be enough to generate alpha. Basically, the "grasp" of the problem is slow.

Here is the place where we lose, and LLMs would win.

The beautiful thing about LLMs that differentiates from working with humans -

When I ask it something like "generate x. Here are a few examples," it delivers alpha that average or below-average workers can't.

If the task is too complex, you need more examples, and it will deliver results.

Flappy Flight 🛩️

One-shotted this using Cursor. There are a lot of issues like the score not updating. Physics issues, etc.

But amazed, really!

Suddenly while doing something, this window comes up on the Mac.

Do you see this often?

It's one of those unfortunate things apple built in the whole scheme!

PS: I moved to Claude Haiku.