Work in progress: 181,232 of 181,233 sites checked so far, more every week · updated 2 Nov 2026Missing a blog? Tell us

Top all-time · #19942

U

Utkarsh Kanwat

Personal blog · utkarshkanwat.com/writingaiprogrammingcareer

Utkarsh Kanwat's personal blog at utkarshkanwat.com covers ai, programming and career. Since 2025, 3 different Hacker News readers have linked it 3 times. No feed was found, so read it on the site itself.

No feed foundVisit the blog
3mentions?
3HN people?
2025–2025first – last linked?

Too few sampled comments (2) to say how often HN recommends it.?

Why HN links it

HN readers link these posts on AI agent hype and what works in production. The only comment on the writing dismisses a quoted line from one of the site's posts as slop.

Summarised by Claude from a sample of 2 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.

AI Research Engineer at AutonomyAI building AI coding agents. Previously built production LLM and RAG systems at ANZ. Published researcher from IIT Bombay specializing in computer vision and deep learning.

What Hacker News says?

  1. > In a Nutshell > AI tools aren't perfect yet. They sometimes make mistakes, and they can't always understand what you are trying to do. But they're getting better all the time, In the future, they will be more powerful and helpful. They'll be able to understand your code even better, and they'll be able to generate even more creative ideas. From another post on the same site. [0] Yup, slop. [0]: https://utkarshkanw…

    Comment linking /writing/review-of-coding-tools/

    on “The current hype around autonomous agents, and what actually works in production”
  2. Submitted The current hype around autonomous agents, and what actually works in production as a story · 427 points

    HN discussion
  3. We’ve been heads-down building and testing Fei, our autonomous engineering agent, and wanted to share the launch. Over the last months, we pushed Fei across a wide variety of projects to see how well our Agentic Context Engine (ACE) personalizes to each repo. What we found is that the way you build an agent matters a lot: We developed our approach to work so that the agents doesn't fall apart because of cascading er…

    Comment linking /writing/betting-against-agents/?utm_source=chatgpt.com

    on a deleted thread

Search all of HN for utkarshkanwat.com