Live data from Hacker News

Viewing profile — insumanth

insumanth

HN member
Joined
Tue, Apr 14, 2026, 5:14 AM UTC
HN karma
44
Public activity
39 items

About insumanth

Building Clyro (runtime governance for AI agents)

Recent public activity

  1. story
  2. comment
    Comment #49082785

    > library dependencies are either distributed with the distribution or are statically linked. I have messed up my packages multiple times and have feared installing anything due to…

  3. comment
    Comment #49082733

    Anyone not doing distributed training across thousands of GPU, pytorch is the best option. Others have an infra team to work on it.

  4. comment
    Comment #49082705

    Opus models were straightforward to review. But Opus 5 is very different.

  5. comment
    Comment #49082692

    I was confused when google acquired "Wiz" for so much money But now, it makes sense to some extent. Security is non-negotiable in AI Era

  6. comment
    Comment #49079821

    We are ok with Open Weight models unless they are far weaker than our closed weight models and we and only we have control over them

  7. comment
    Comment #48582888

    Multi-Modal is the way to go. Deepmind nailed this a long back.

  8. comment
  9. comment
    Comment #48539171

    >> The bad guys won’t rest > Probably not. But we will. This is Exceptional. Perfect EuroMaxxing

  10. comment
    Comment #48539119

    This was expected. Apple will carefully choose what & how people can use AI in their ecosystem and will make sure of it. I hope "Apple Foundation Models" Eco-system grows with supp…

  11. comment
    Comment #48537231

    As I read this, all of my favorite things about ruby compared to something like python were influenced by lisp. Ruby is a joy to program and it seems mostly due to design influence…

  12. comment
    Comment #48537207

    I have always been fascinated by Hash Functions. Modern hash functions are incredibly fast and unbelievably secure (crypto hashes). Also, equally important is how hashes have adopt…

  13. comment
    Comment #48537160

    I will be doing these things with local LLMs Take a fast, small and powerful LLM running locally to index my personal data like images, videos, documents and enrich them and tag wi…

  14. comment
    Comment #48537125

    This mostly applies to almost any database. Deletes are Writes and Writes are resource intensive. This is more prominent on databases like Elastic Search. When I was tasked to dele…

  15. comment
    Comment #48537087

    > that bloated pinnacle of software that is 80% about DRM, 20% about the reading experience I have never seen someone explain the adobe software so perfectly. Using any adobe softw…

  16. comment
    Comment #48500380

    I honestly don't think this is bad. For anyone who is not a frontend engineer / designer, using tailwind gives good defaults and better LLM support. Frameworks were always about lo…

  17. comment
    Comment #48500287

    > MiMo Code is a terminal-based coding agent built by Xiaomi's MiMo team on top of OpenCode and open-sourced under the MIT license. I think it is great that they built it on top of…

  18. comment
    Comment #48500261

    > If Fable had been acting on malicious instructions—a prompt injection attack ... it’s alarming to think quite how far it could go to exfiltrate data or cause other forms of misch…

  19. comment
    Comment #48500236

    Boring is Better

  20. comment
  21. comment
  22. comment
  23. comment
  24. comment
  25. comment
    Comment #48486636

    I'm worried at the general direction of this. More and more companies will gatekeep the model capability even if it is just a few percent increase in capabilities than other models…