Hacker News: rohitpaulk

New comment by rohitpaulk in "RubyLLM: A Ruby framework for all major AI providers"

rohitpaulk — Wed, 24 Jun 2026 17:33:09 +0000

We use RubyLLM in production too, the most elegant library in this space I've seen so far.

I also liked how they run the issue tracker. If you select "Feature Request", it makes you explain how you explored workarounds, why you believe it belongs in RubyLLM etc to prevent scope creep.

New comment by rohitpaulk in "Ember.js 7.0"

rohitpaulk — Sat, 30 May 2026 07:32:35 +0000

Same here. Loved the LTS thinking and Ember data being built in but hiring was a pain and ecosystem packages were often out of date.

New comment by rohitpaulk in "A new EDIT tool for LLM agents"

rohitpaulk — Tue, 19 May 2026 07:40:21 +0000

Prior art: https://blog.can.ac/2026/02/12/the-harness-problem/

New comment by rohitpaulk in "Rewrite Bun in Rust has been merged"

rohitpaulk — Thu, 14 May 2026 11:34:07 +0000

The whole idea that my RUNTIME contains code that a single human hasn't looked at does make me uncomfortable, but if this actually works without a ton of issues it's pretty remarkable.

New comment by rohitpaulk in "Interaction Models"

rohitpaulk — Mon, 11 May 2026 22:00:09 +0000

Aside from how impressive the model is, the demos here are very well done! Quirky and short, unlike what we're used to from Anthropic and OpenAI.

New comment by rohitpaulk in "YC's Biggest Scandals"

rohitpaulk — Sun, 10 May 2026 19:56:48 +0000

Only a portion of these are "scandals", the rest are just usual startup failures.

New comment by rohitpaulk in "Cloudflare to cut about 20% of its workforce"

rohitpaulk — Thu, 07 May 2026 20:43:32 +0000

That's 2 major layoffs this week (Coinbase being the other). Is there an underlying common reason for this? And is it indeed AI-driven productivity as both companies claim?

Yann LeCun's Billion Dollar Bet [video]

rohitpaulk — Sun, 03 May 2026 15:17:33 +0000

Article URL: https://www.youtube.com/watch?v=kYkIdXwW2AE

Comments URL: https://news.ycombinator.com/item?id=47997802

Points: 3

# Comments: 0

New comment by rohitpaulk in "Cursor Camp"

rohitpaulk — Thu, 30 Apr 2026 03:44:41 +0000

Nice one. Pleasantly surprised that this has nothing to do with Cursor the IDE

New comment by rohitpaulk in "Laguna XS.2 and M.1"

rohitpaulk — Tue, 28 Apr 2026 16:25:48 +0000

Been testing these via their "pool" agent. It's fast, and the agent adheres to the ACP spec pretty well (better than codex, opencode etc.) so it's a good experience in Zed.

New comment by rohitpaulk in "We've raised $17M to build what comes after Git"

rohitpaulk — Fri, 10 Apr 2026 09:36:11 +0000

Most of the comments here are clearly from people who haven't used GitButler. Try it out and it's a very sticky product, clearly superior workflow to vanilla Git.

New comment by rohitpaulk in "Weave – A language aware merge algorithm based on entities"

rohitpaulk — Wed, 04 Mar 2026 11:45:51 +0000

Saw this on Twitter a few weeks ago, interesting approach.

The post links to the GitHub repo, but imo the website does a better job of explaining what it does: https://ataraxy-labs.github.io/weave/

New comment by rohitpaulk in "OpenAI fires an employee for prediction market insider trading"

rohitpaulk — Sat, 28 Feb 2026 22:07:37 +0000

Two questions I'd have expected the article to answer:

(a) how did they identify the employee, and (b) how come they weren't sent to jail

New comment by rohitpaulk in "Oat – Ultra-lightweight, zero dependency, semantic HTML, CSS, JS UI library"

rohitpaulk — Sun, 15 Feb 2026 09:55:59 +0000

Surprised that none of the comments here are comparing this to Bootstrap.

Why does request.remote_ip work on Heroku but not Render?

rohitpaulk — Fri, 13 Feb 2026 16:37:33 +0000

Article URL: https://rohitpaulk.com/articles/render-rails-remote-ip

Comments URL: https://news.ycombinator.com/item?id=47004634

Points: 1

# Comments: 0

New comment by rohitpaulk in "Improving 15 LLMs at Coding in One Afternoon. Only the Harness Changed"

rohitpaulk — Fri, 13 Feb 2026 03:49:13 +0000

This sounds like a good optimization task to give a long-running agent. Ask it to come up with experiments and maximize the % of successful edits.

CCBench: How do agents perform on codebases that aren't part of training data?

rohitpaulk — Thu, 12 Feb 2026 22:25:25 +0000

Article URL: https://ccbench.org/

Comments URL: https://news.ycombinator.com/item?id=46996165

Points: 1

# Comments: 0

New comment by rohitpaulk in "Crafting Interpreters"

rohitpaulk — Thu, 15 Jan 2026 02:23:28 +0000

In case anyone finds it useful, we (CodeCrafters) built a coding challenge as a companion to this book. The official repository for the book made this very easy to do since it has tests for each individual chapter.

Link: https://app.codecrafters.io/courses/interpreter/overview

Code a database in 45 steps: test-driven coding puzzles

rohitpaulk — Fri, 26 Dec 2025 19:36:28 +0000

Article URL: https://trialofcode.org/database/

Comments URL: https://news.ycombinator.com/item?id=46395373

Points: 2

# Comments: 0

New comment by rohitpaulk in "Gemini 3 Flash: Frontier intelligence built for speed"

rohitpaulk — Wed, 17 Dec 2025 17:09:40 +0000

Wild how this beats 2.5 Pro in every single benchmark. Don't think this was true for Haiku 4.5 vs Sonnet 3.5.