Arnav Praneet

I don't want to believe. I want to know.

[Arnav Praneet @arnav_praneet]

No wonder he kept running out of session limits on a Max plan
Also I am as lazy as they come with regards to this sort of stuff, I basically always use VS code's version control UI to commit but it's still genuinely 2-3 clicks man please save some time at least

[Arnav Praneet @arnav_praneet]

Had an intern working through a complex problem on screen share and I lost it when the guy just asked Opus 4.7 to run git commit and git push for him

[Arnav Gupta @championswimmer]

I actually feel sorry for Uber

$1500 per month can be very low if your engineers have gotten used to stupidity like asking Opus 4.7 to do git commit.

But then again, "token efficiency" workstreams will create a lot of promo packets, as it happens in bigtech all the time.

[Tricia Dearborn @TriciaDearborn]

A list of resources for people who want to resist the uncritical adoption of AI. I've only read the first, but it's a corker. Like getting shaken by the shoulders, smacked around the chops & given a lifesaving dose of the elixir of truth at the same time
https://t.co/gDP0SlYuta

[Arnav Praneet @arnav_praneet]

It took over all my files when I accidentally opened Windows backup to prepare to switch to Linux 😭
Every documents folder got mixed with years old stuff and backed up forcibly

[Arnav Praneet @arnav_praneet]

Anyone who worked on the OneDrive - Windows 11 integration needs to suffer greatly in life.

[Arnav Praneet @arnav_praneet]

@_svs_ Possibly good news for me if rumours are true

[Arnav Praneet @arnav_praneet]

About to drop an open source took today

[Arnav Praneet @arnav_praneet]

You have to dress up like a tuxedo cat for formal events

[Arnav Praneet @arnav_praneet]

India AI Summit because they didn't invite Bezos

[Arnav Praneet @arnav_praneet]

Anyone going to John Mayer in Mumbai tomorrow?

[kenneth @kennethnym]

still cant believe tailscale and cloudflare tunnels are free

[appycot jam @apricotjamcam]

baby meow (she proceeded to bunny kick and bit my hand after this)

[Arnav Praneet @arnav_praneet]

@sadekships @marclou @sadekships could you check DMs?

[Arnav Praneet @arnav_praneet]

https://t.co/MY36JlOSl3

[pnorm @paleonormie]

oh sick we're finally gonna get a decent embeddings model that lets you "similarity search" music

[Arnav Praneet @arnav_praneet]

@AashaySachdeva @NirantK What are you doing that's different? Seems to work the same for me if I give it well defined tasks, i switch in glm for claude all the time whenever my claude agents are busy

[Arnav Praneet @arnav_praneet]

https://t.co/icpeFnE4q1

[Arnav Praneet @arnav_praneet]

List of all the mentioned books on HackerNews in 2025

Try guessing the top one with 209 mentions without opening

[Arnav Praneet @arnav_praneet]

They downloaded the entirety of Spotify?!?!

[Andrej Karpathy @karpathy]

Quick new post: Auto-grading decade-old Hacker News discussions with hindsight

I took all the 930 frontpage Hacker News article+discussion of December 2015 and asked the GPT 5.1 Thinking API to do an in-hindsight analysis to identify the most/least prescient comments. This took ~3 hours to vibe code and ~1 hour and $60 to run. The idea was sparked by the HN article yesterday where Gemini 3 was asked to hallucinate the HN front page one decade forward.

More generally:

1. in-hindsight analysis has always fascinated me as a way to train your forward prediction model so reading the results is really interesting and
2. it's worth contemplating what it looks like when LLM megaminds of the future can do this kind of work a lot cheaper, faster and better. Every single bit of information you contribute to the internet can (and probably will be) scrutinized in great detail if it is "free". Hence also my earlier tweet from a while back - "be good, future LLMs are watching".

Congrats to the top 10 accounts pcwalton, tptacek, paulmd, cstross, greglindahl, moxie, hannob, 0xcde4c3db, Manishearth, and johncolanduoni - GPT 5.1 Thinking found your comments to be the most insightful and prescient of all comments of HN in December of 2015.

Links:
- A lot more detail in my blog post https://t.co/7LpJEVgbyk
- GitHub repo of the project if you'd like to play https://t.co/WVQUbUzt2y
- The actual results pages for your reading pleasure https://t.co/e2XIYElnc5