Hacker News: aravindputrevu

New comment by aravindputrevu in "Cloudflare acquires Deno"

aravindputrevu — Fri, 09 Oct 2026 15:16:24 +0000

Last year it was bun, and now it is - Deno!

What's happening to JS platforms? I thought Deno has a much better approach to building a platform.

New comment by aravindputrevu in "GitHub Has Restricted Access to Star Data"

aravindputrevu — Tue, 07 Jul 2026 14:40:42 +0000

Star history is a great project. I am sad i will not be able to see the star chart, however, people have abused the system for far too long! So this is coming.

Jet Engine on a Tractor: AI's Big Productivity Trap

aravindputrevu — Tue, 07 Jul 2026 04:56:52 +0000

Article URL: https://www.uptimelabs.io/articles/jet-engine-on-a-tractor-ais-big-productivity-trap

Comments URL: https://news.ycombinator.com/item?id=48813813

Points: 2

# Comments: 0

New comment by aravindputrevu in "You Don't Know Jack About Formal Verification"

aravindputrevu — Tue, 07 Jul 2026 04:55:20 +0000

Sorry, did not realize that it was submitted.

You Don't Know Jack About Formal Verification

aravindputrevu — Mon, 06 Jul 2026 20:31:57 +0000

Article URL: https://queue.acm.org/detail.cfm

Comments URL: https://news.ycombinator.com/item?id=48810122

Points: 3

# Comments: 3

New comment by aravindputrevu in "AI Agent Has Amnesia"

aravindputrevu — Wed, 22 Apr 2026 17:59:47 +0000

Hi, I work for CodeRabbit.

We have been building agents for code review workflow for nearly two years. Our Code Review Knowledge base today serves more than 3 million repos. We pack more than 40 different points of information into the same LLM context, such as MCP Servers, Rule files, etc. We understand context poisoning/rot and how it creating problems.

We are now bringing the same learning/context engine to SDLC and Slack.

Please give it a try!

New comment by aravindputrevu in "Claude in Chrome"

aravindputrevu — Sun, 21 Dec 2025 14:45:14 +0000

So far, less impressive. Hope it gets better.

The rise of 'Slow AI': Why devs should stop speedrunning stupid

aravindputrevu — Wed, 05 Nov 2025 18:26:37 +0000

Article URL: https://www.coderabbit.ai/blog/the-rise-of-slow-ai-why-devs-should-stop-speedrunning-stupid

Comments URL: https://news.ycombinator.com/item?id=45826124

Points: 1

# Comments: 0

Who's funding open-source in 2025? A guide for maintainers

aravindputrevu — Tue, 23 Sep 2025 14:56:46 +0000

Article URL: https://www.eliostruyf.com/whos-funding-open-source-2025-guide-maintainers/

Comments URL: https://news.ycombinator.com/item?id=45347977

Points: 2

# Comments: 0

New comment by aravindputrevu in "Atlassian is acquiring The Browser Company"

aravindputrevu — Thu, 04 Sep 2025 14:40:00 +0000

Would Atlassian be building a agentic version for their AI Coding agent - Rovo.

Atom: GitHub's Forgotten Editor

aravindputrevu — Thu, 04 Sep 2025 14:39:03 +0000

Article URL: https://www.youtube.com/watch?v=f11W2SsXh_E

Comments URL: https://news.ycombinator.com/item?id=45127810

Points: 5

# Comments: 0

New comment by aravindputrevu in "CocoaPods trunk read-only plan"

aravindputrevu — Mon, 01 Sep 2025 11:39:27 +0000

Isnt this a old news? I'm thinking of Swift Package manager for all the stuff new.

New comment by aravindputrevu in "Benchmarking GPT-5"

aravindputrevu — Fri, 08 Aug 2025 16:27:36 +0000

We put GPT-5 through our Golden PR Dataset.

Here is the TL;DR

- GPT-5 outperformed Opus-4, Sonnet-4, and OpenAI’s O3 across a battery of 300 varying difficulty, error-diverse pull requests.

- GPT-5 scored highest on our comprehensive test and found 254 out of 300 bugs or 85% where other models found between 200 and 207 – 16% to 22% less.

- On our 25 hardest PRs from our evaluation dataset, GPT-5 achieved the highest ever overall pass rate (77.3%), representing a 190% improvement over Sonnet-4, 132% over Opus-4, and 76% over O3.

Benchmarking GPT-5

aravindputrevu — Fri, 08 Aug 2025 16:27:36 +0000

Article URL: https://www.coderabbit.ai/blog/benchmarking-gpt-5-why-its-a-generational-leap-in-reasoning

Comments URL: https://news.ycombinator.com/item?id=44838865

Points: 9

# Comments: 1

The Art and Science of Context Engineering for AI Code Reviews

aravindputrevu — Thu, 17 Jul 2025 23:59:46 +0000

Article URL: https://www.coderabbit.ai/blog/the-art-and-science-of-context-engineering

Comments URL: https://news.ycombinator.com/item?id=44599696

Points: 1

# Comments: 0

An Analysis of Search Benchmark, the Game

aravindputrevu — Wed, 21 May 2025 10:48:23 +0000

Article URL: https://jpountz.github.io/2025/05/12/analysis-of-Search-Benchmark-the-Game.html

Comments URL: https://news.ycombinator.com/item?id=44050105

Points: 2

# Comments: 0

New comment by aravindputrevu in "OpenAI reaches agreement to buy Windsurf for $3B"

aravindputrevu — Tue, 06 May 2025 13:54:33 +0000

I still can't believe how they let Cursor (which is amazing until somepoint) take away all the shine.

This reminds me of "big companies moves slow.." line.

New comment by aravindputrevu in "OpenAI reaches agreement to buy Windsurf for $3B"

aravindputrevu — Tue, 06 May 2025 13:53:36 +0000

I completely disagree and feel MS would never do it. Not a MS Employee, but they have moved on from such battles.

They should have restricted the Marketplace several years ago, however, they are doing it now.

With C++, they are part of MFC's, they are the legal owners, not like Google vs Oracle in case of Java.

Lastly, with AI Code IDEs I think yes, there is a case, the need for IDE might be very less. Like a steering on a self driving car.

New comment by aravindputrevu in "Botswana launches first satellite BOTSAT-1 aboard SpaceX Falcon 9"

aravindputrevu — Wed, 26 Mar 2025 22:32:33 +0000

So true. I think most people don't realise how hard it is really to build a engine that works.

New comment by aravindputrevu in "Gemma3 – The current strongest model that fits on a single GPU"

aravindputrevu — Wed, 12 Mar 2025 10:36:27 +0000

I'm curious. Is there any value to do these OSS models?

Suddenly after reasoning models, it looks like OSS models have lost their charm