Hacker News: amitav1

New comment by amitav1 in "Kimi Claw"

amitav1 — Sat, 21 Feb 2026 19:16:10 +0000

I prefer OpenClaw because it's more persistent. I know, I know, theoretically you could do the same thing with Claude Code and markdown files (which, to be fair, is pretty much how OpenClaw works), I guess it's mostly the telegram interface I like. Most of the time I don't have my laptop with me, and ssh using Termux, and opening a remote claude code is a much greater hassle than sending a telegram message, and with telegram (or whatsapp or discord or whatever) you get the benefit of being able to send voice messages, which I find very useful. In what way is Clawdbot "insane"? Obviously if you give it write access to your email and twitter and whatnot, that's not great, but for me I really just give it access to that probably wouldn't ruin my life / career if they got out (e.g. my class notes and Anki decks).

New comment by amitav1 in "Kimi Claw"

amitav1 — Sat, 21 Feb 2026 17:31:47 +0000

I don't see why not, but I also have no experience in that sort of stuff, so take my endorsement with a grain of salt

New comment by amitav1 in "Kimi Claw"

amitav1 — Mon, 16 Feb 2026 04:46:34 +0000

By schedule my tasks throughout the day, I mean that it will figure out when I should do each thing, not that it does all of the things for me.

New comment by amitav1 in "Kimi Claw"

amitav1 — Sun, 15 Feb 2026 16:19:33 +0000

Personally, I use it to manage all of the stuff I don't want to. I give it my course content and it makes flashcards for me to review. I give it my tasks and it schedules them throughout the day. All of the menial stuff that is necessary but not productive. It also has a much better memory than I do on account of it's constant access to a filesystem and grep. It's like my personal assistant and tutor and guidance counsellor and sysadmin, all in one. I do think that a) you need to stick with it for a few days and b) use a good model. When I first started using it, it was just a worse version of ChatGPT, but after bringing in all of my data from ChatGPT it's a lot easier for it to search for stuff when it's confused. Now it can also do stuff like manage nginx or my sync serviceand whatnot, ~autonomously. Originally I was using locally running qwen models, but they were so timid as to be useless. Right now I'm using Kimi 2.5 as my model.

New comment by amitav1 in "Self Driving Car Insurance"

amitav1 — Sat, 31 Jan 2026 00:36:20 +0000

Because LLCs aren't people

New comment by amitav1 in "Prism"

amitav1 — Tue, 27 Jan 2026 22:43:15 +0000

Am I missing something? LaTeX is associated with slop now?

New comment by amitav1 in "Prism"

amitav1 — Tue, 27 Jan 2026 22:40:05 +0000

How would this work for independent researchers?

(no snark)

New comment by amitav1 in "Microsoft gave FBI set of BitLocker encryption keys to unlock suspects' laptops"

amitav1 — Fri, 23 Jan 2026 19:37:31 +0000

I can't think of anybody apart from Osama bin Laden who wouldn't want to play Candy Crush. \s

New comment by amitav1 in "Microsoft gave FBI set of BitLocker encryption keys to unlock suspects' laptops"

amitav1 — Fri, 23 Jan 2026 19:34:05 +0000

Something with KDE. Never used KDE extensively because I hate non-tiling WMs, but something like Kubuntu would give you a more windows-esque experience by default. Here's the download link:

https://kubuntu.org/download/

Bon appetit!

New comment by amitav1 in "GPTZero finds 100 new hallucinations in NeurIPS 2025 accepted papers"

amitav1 — Thu, 22 Jan 2026 20:34:06 +0000

I guess the way one would verify that this is more general trend in academia would be to run this on accepted papers to a non-AI conference?

New comment by amitav1 in "Show HN: Bible translated using LLMs from source Greek and Hebrew"

amitav1 — Thu, 22 Jan 2026 19:16:21 +0000

It was slow to load for me but loaded eventually.

New comment by amitav1 in "GPTZero finds 100 new hallucinations in NeurIPS 2025 accepted papers"

amitav1 — Thu, 22 Jan 2026 17:38:35 +0000

I'm doing some research, and this is something I'm unsure of. I see that "suppressing null results" is a bad thing, and I sort of agree, but for me personally, a lot of the null results are just the result of my own incompetence and don't contain any novel insights.

New comment by amitav1 in "OpenAI to begin testing ads on ChatGPT in the U.S."

amitav1 — Wed, 21 Jan 2026 19:41:21 +0000

I mean, to steelman their point, there's a lot more misinformation than information on Google. I still personally think that it's a worthwhile trade though

New comment by amitav1 in "Reducing Dependabot Noise"

amitav1 — Sat, 17 Jan 2026 21:08:19 +0000

I believe so

New comment by amitav1 in "OpenAI to begin testing ads on ChatGPT in the U.S."

amitav1 — Fri, 16 Jan 2026 19:05:09 +0000

> "it objectively made the search product worse"

I would disagree, because without the advertising there probably would be no Google.

New comment by amitav1 in "OpenAI to begin testing ads on ChatGPT in the U.S."

amitav1 — Fri, 16 Jan 2026 19:02:55 +0000

Google is one the most important institution of the Internet era. Talk all you'd like about "OoOoH tHeY aDvErTiSe" or "tHeiR aLgOrItHm Is GeTtInG wOrSe" but at the end of the day, Google still brought knowledge to more people than anything before (apart from maybe Gutenberg).

New comment by amitav1 in "OpenAI to begin testing ads on ChatGPT in the U.S."

amitav1 — Fri, 16 Jan 2026 18:59:59 +0000

The way you phrased this makes it sound like he's a shill, but his takes about AI don't seem unusually complementary.

New comment by amitav1 in "Cloudflare acquires Astro"

amitav1 — Fri, 16 Jan 2026 16:46:00 +0000

"I don't care, it's a stupid question."

New comment by amitav1 in "How have prices changed in a year? NPR checked 114 items at Walmart"

amitav1 — Wed, 14 Jan 2026 19:44:01 +0000

Take my upvote and leave this platform forever

New comment by amitav1 in "Ask HN: Share your personal website"

amitav1 — Wed, 14 Jan 2026 19:02:31 +0000

https://amitav.net