Parth

Software Engineer

[Parth @Parth_dedhia98]

@RyanSael Really nice.

[Ryan Sael @RyanSael]

I asked Opus 5.5 to explain camera focus by building an interactive lens lab

Here's what it came up with after 1 hour 26 minutes in one shot, $25.66 API cost
https://t.co/uqDgUs8H9h

Move the focus ring and you can see the glass elements shift the sharp plane through the scene

[Parth @Parth_dedhia98]

https://t.co/WRWfyEUScj

@IRCTCofficial itself charges extra 2% on credit card 😅

[Parth @Parth_dedhia98]

Recent TUI update from claude code is 🙌🙌

[Parth @Parth_dedhia98]

@trq212 @bcherny
The claude code in the claude application as well as in vs code extension show a progress showing the context usage as well as limit. But the TUI doesn't. Can we include this in default. I wouldn't want to add a /usage during ongoing conversation.

[Parth @Parth_dedhia98]

@kimmonismus Yes.
For mundane work

[Parth @Parth_dedhia98]

@bcherny @ClaudeDevs Could you just share what would be a permenant fix for this?
I thought what you did in this update was permanent 😅

[Parth @Parth_dedhia98]

@ClaudeDevs Much needed. Thanks.
I had explicit instructions in CLAUDE.md just for this.

[Parth @Parth_dedhia98]

@elonmusk @nottombrown @grok Wasn't Elon Musk against anthropic. I remember previously him saying the company is unanthropic and all? So what changes now?

[Parth @Parth_dedhia98]

@trq212 @bcherny
We can reduce the token usage of reading the files by maintaining the hash of each file. If the file has not changed since claude code has last read, we can avoid re-reading it and tell it to use from memory.
Very naive idea! But could save some token.

[Parth @Parth_dedhia98]

@elonmusk would you consider adding double tap on a X post to like it?
Easier experience i guess.

[Dustin @r0ck3t23]

Dario Amodei just dismantled the biggest myth in the AI industry.

Open source AI isn’t free. It never was.

Amodei: “It’s not free. You have to run it on inference and someone has to make it fast on inference.”

For decades, open source meant something real. It meant a teenager in a basement could download the same tools as a Fortune 500 company. Could read the code. Could modify it. Could build something that competed with the giants.

That was genuine democratization. That actually happened.

AI is different. Fundamentally. Physically. In ways the ideology hasn’t caught up to yet.

Downloading the weights is the easy part.

The part that actually costs something is turning the weights into a running system. Into responses. Into intelligence operating in real time at scale.

That requires compute. Power. Infrastructure. The kind measured in billions of dollars and years of construction.

Amodei: “These are big models. They’re hard to do inference on. Ultimately you have to host it on the cloud. The people who host it on the cloud do inference.”

The open source debate was never about who owns the model.

It was always about who owns the cloud.

And Amodei goes further. When a competitor drops a new open model, he doesn’t ask whether it’s open or closed. He doesn’t care about the licensing. He doesn’t engage the ideology.

Amodei: “I don’t think it mattered that DeepSeek is open source. I think I ask, is it a good model? Is it better than us at the things that matter? That’s the only thing that I care about.”

That’s the ruthless clarity of someone actually trying to win.

While the media debates licensing frameworks, Amodei is asking one question.

Is it better. Everything else is a distraction.

Amodei: “I don’t think open source works the same way in AI that it has worked in other areas. Here we can’t see inside the model.”

This isn’t Linux. You can’t read it. You can’t fork it. You can’t understand it the way generations of developers understood the tools they inherited.

You can download it. And then you need a data center to run it.

The teenager in the basement who was supposed to be empowered by this revolution needs a billion dollars of infrastructure before the empowerment starts.

The era of the basement coder rewriting civilization on a laptop is over.

The future belongs to whoever commands the compute, owns the power grid, and can actually turn the intelligence on.

Open weights without infrastructure isn’t democratization.

It’s a promise the physics of the universe won’t let us keep.

[Parth @Parth_dedhia98]

When I saw videos of @bcherny describing how he built claude code, I thought he must be hiding something in plain sight.
Then I tried to build something on the same line, gave access to the filesystem and bash tools to LLM and I was quite surprised how nicely they worked. 🤯🤯

[Rajesh Dedhia @rkdedhia]

@RailMinIndia @RailOneIndia @IRCTCofficial @PMOIndia

I attempted to book Tatkal tickets again today and was denied, with the reason provided being that only Aadhaar-authenticated individuals can book tickets. Where asI am already authenticated. I have attached a screenshot.

[Parth @Parth_dedhia98]

@RailMinIndia @IRCTCofficial @RailwaySeva @RailMadad
The tatkal booking doesn't work at all from RailOne application. This is the third time I tried, and it's still not working. If the tatkal booking is ot working, then kindly allow me get refund of money added to the wallet

[Parth @Parth_dedhia98]

@airindia Increasing fare makes sense, not the other way round. Like I said, it feels cheated. And why is your system showing "x tickets left" when clearly there are more. False demand creation - clearly a dark pattern to create a sale.

[Parth @Parth_dedhia98]

@airindia unhappy by the dynamic pricing. Tkts purchased two days ago cost almost 2x today's price. Feels cheating. Given recent incidents, you guys don't stand a leg to play with prices. I did not want to raise it on a public platform, but complaint tickets did not help.

[Parth @Parth_dedhia98]

@AravSrinivas @perplexity_ai You have built something wonder.
Pls fix: Switching app from perplexity, while a query is running, and then coming back to perplexity causes it to fail saying 'retry'. If I go on threads, and come to the same query, it works. Happens on my android.

[Computer @AskPerplexity]

🚨 BREAKING: Trump has officially signed an executive order imposing a $100K annual fee for H-1B visas.

Why did the US do this? How does this affect the 400,000 immigrants who come to the US each year on H-1B visas? And what’s next?

Here’s the full story:

[Rajesh Dedhia @rkdedhia]

@tvsmotorcompany Hahaha high performance brand??? Noway, the most worst performance award milna chahiye tha. 1 small complaint need so many follow- ups. Don't understand why such a long procedure. How you deserve such awards. Very very bad experience.