Hacker News: rshanreddy

New comment by rshanreddy in "Ask HN: Who is hiring? (July 2026)"

rshanreddy — Wed, 01 Jul 2026 19:13:26 +0000

Aristotle (https://www.heyaristotle.com/careers)

Applied AI lab working on the future of education

New comment by rshanreddy in "Cowork: Claude Code for the rest of your work"

rshanreddy — Tue, 13 Jan 2026 22:03:34 +0000

Have still not been able to get a query to work. "Sending request" or other errors at every turn.

New comment by rshanreddy in "New benchmark shows top LLMs struggle in real mental health care"

rshanreddy — Wed, 10 Dec 2025 19:32:43 +0000

This is a 1250 word judging prompt - likely AI generated Along with 10 scored conversation samples - all also AI generated No verification in the field, no real data

In other words, AI scores on AI conversations - disguised as a means of gauging clinical competence / quality?

This is not an eval - this is a one-shotted product spec!

New comment by rshanreddy in "US Tech Market Treemap"

rshanreddy — Fri, 14 Nov 2025 20:27:44 +0000

Super clean and instantly legible. Great to have a clean, up-to-date tech-only treemap, glad this exists!

A few suggestions: 1) Sector/subsector drill-downs (AI, cloud, semis, autos) so you can zoom into sectors/clusters 2) Hover/tap cards with basics like revenue, P/E, EV/EBITDA, or YTD return 3) AI “explanations mode”: tap a ticker -> auto-generate a 1-sentence summary of why it moved today (“AMD up 3%: fabs reporting stronger wafer starts; NVDA sympathy move”)

Congrats on the ship @krkb :)

New comment by rshanreddy in "Show HN: A Digital Twin of my coffee roaster that runs in the browser"

rshanreddy — Fri, 10 Oct 2025 20:44:43 +0000

super cool

New comment by rshanreddy in "Learn Your Way: Reimagining Textbooks with Generative AI"

rshanreddy — Thu, 18 Sep 2025 20:03:06 +0000

whoa this is fantastic. wish I had known about this earlier! just made a similar product for reading arXiv / epub / pdfs called Ruminate (www.tryruminate.com), would love to hear what you think

Show HN: Ruminate – AI reading tool for understanding hard things

rshanreddy — Mon, 15 Sep 2025 19:50:17 +0000

We made Ruminate over the past few weeks because we were frustrated with how hard it is to read complex text with LLMs - research papers, novels, long articles, etc.

We found ourselves copy-pasting the text/file into ChatGPT, having chats about different parts of the text in different tabs, and bummed we couldn't easily track the best insights from all those conversations in one place. We wanted one place where we could stay immersed in the text, dip into lengthy and generative rabbitholes when we wanted to (in an unobtrusive way), and have a 'work product' of your learning process (all your notes in one place). No more tab switching - one unified interface centered around the text itself.

With Ruminate, you can: 1) Upload PDFs, EPUBs, or web articles and read them in our custom reader (PDF upload done with https://github.com/datalab-to/marker; headless browser automation for web articles) 2) Highlight text to ask questions, get definitions, or discuss with an LLM (that has context on the whole document, the pages you've read, and will web search too) 3) Save notes, definitions, and annotations (and view them all later in their own tabs)

There are loads of ways to use an LLM to save you time and offload thinking/learning/cognition - we want this to be a tool that actually enables/empowers you to think more deeply and understand more.

Would love your feedback - on the product, the concept, or even your own experiences trying to learn from difficult material (or learn with LLMs broadly). Much appreciated.

Comments URL: https://news.ycombinator.com/item?id=45254155

Points: 18

# Comments: 3

New comment by rshanreddy in "Show HN: I Vibe Coded Doge Decimator in Websim [video]"

rshanreddy — Thu, 27 Mar 2025 21:47:42 +0000

this is sick