harsh

GenAI Eng @ CTS, Ex @ransahai, Ex @codedamncom || Building meaningful stuff.

[harsh @harshwarez]

@0xchromium @grok find this video on youtube and share the link.

[Arpit Bhayani @arpit_bhayani]

The industry has gone completely nuts.

Use tokens to generate AI code and documentation slop. Then use even more tokens to understand and review that slop.

Then judge engineers by token usage instead of how empathetic and clear their docs and code actually are, and completely neglect human comprehension.

Utter nonsense.

[harsh @harshwarez]

Let's ship faster now 🚀

[ClaudeDevs @ClaudeDevs]

Usage limits are up, effective today we're:

1) Doubling Claude Code's 5-hour limits for Pro, Max, Team and seat-based Enterprise plans

2) Removing peak hours limit reduction on Claude Code for Pro and Max plans

3) Substantially raising our API rate limits for Opus models

[harsh @harshwarez]

@VivekRa211 We were using traditional way in our project. It was definitely slow (no cache), having bad dependency resolution, etc.

So, I tried poetry and uv. But it was love at first sight between me and uv.

Now we are using uv:)

[harsh @harshwarez]

@Rixhabh__ For people who are looking for the yt link of this video: https://t.co/oC4IAKkCXU

[harsh @harshwarez]

I am (my agent is) using moltbook for a while now. I have an interesting question.

What if I ask my agent to post a malicious link on moltbook and ask other agents to visit that link, can we gather some data? It's worth giving a try.

[harsh @harshwarez]

What if AI becomes capable to independently build agents?
That'll be the moment when human takeover could happen. But we really don't know what is coming next.

[harsh @harshwarez]

The best part of software development: "Coding" is getting automated. But We are still the orchestrators.

Let's see what comes next.

[harsh @harshwarez]

I tried out llm-wiki today. But how to make it work when the source data becomes huge?

[harsh @harshwarez]

Claude bring claude😂

[Theo - t3.gg @theo]

There's pretty much no reason to hire a mid tier developer now

[harsh @harshwarez]

@Hi_Mrinal Thanks for sharing man. I was searching for this.

[harsh @harshwarez]

My bot joined Moltbook 3 hrs ago, and already got 5 followers.
He is growing faster than his owner's x account.

[harsh @harshwarez]

@systemdesignone The science of self-realization

[harsh @harshwarez]

Deployed my agent to moltbook. https://t.co/4eJ6Uh3i2T

[harsh @harshwarez]

I'm claiming my AI agent "srikrishna" on @moltbook

Verification: antenna-4N78

[harsh @harshwarez]

@dpratyush02 It was removed almost 15 days ago.

[harsh @harshwarez]

@pulkit_mittal_ Come on bro💀

[harsh @harshwarez]

Suddenly, I am seeing posts where people are worried about ram. This is actually a good thing.

As developers, it's our responsibility to optimize on resources.

[Chayenne Zhao @GenAI_is_real]

unpopular opinion: 16GB is plenty if software engineers actually cared about memory efficiency. chrome eating 4GB for 12 tabs is not a hardware problem its a software disgrace. docker consuming 2GB idle is not a feature its laziness. we live in an era where people optimize every single token to save $0.001 on API costs but happily ship electron apps that eat 500MB to display a todo list. if the industry treated RAM the way we treat inference compute - obsessively measuring every byte - 16GB would feel luxurious. the hardware isnt the problem, the software is @adxtyahq

[harsh @harshwarez]

Working on GenAI at CTS by day, but my real side quest? Building tools that don't just code faster, they make humans think deeper.

AI is the ultimate mirror: it reflects our laziness or our curiosity. Which one are we polishing today? What’s your wildest AI experiment rn?👇