Live data from Hacker News

Viewing profile — makeavish

makeavish

HN member
Joined
Sat, Dec 22, 2018, 5:59 PM UTC
HN karma
132
Public activity
53 items

About makeavish

No profile information was provided.

Recent public activity

  1. comment
    Comment #48722774

    True, I have found it to be valid as well

  2. comment
  3. comment
    Comment #48717055

    I have been at both side of the market. And it sucks so bad at both ends. Companies which deeply care about next hire are struggling to hire and actual great people looking out are…

  4. comment
    Comment #48715271

    Hiring and job search has been so hard and AI has amplified the existing problems instead of solving any.

  5. comment
    Comment #47713793

    Claude launched Managed Agents which fulfills our usecase! https://platform.claude.com/docs/en/managed-agents/overview

  6. comment
    Comment #47684347

    Interesting, let me check it out

  7. story
    Claude Agent SDK vs. Messages API for a Production AI Assistant?

    We're building a chat assistant into our B2B developer tool. It needs to call domain-specific tools (MCP), stream responses (SSE), and persist conversation history. The Claude Agen…

  8. comment
    Comment #47076190

    Yeah maybe that but atleast let us know about this Or have dynamic limits? Nerfing breaks trust. Though I am not sure if they actually nerf it intentionally. Haven't heard from any…

  9. comment
    Comment #47076157

    I don't use AI studio for my work. I used Antigravity/Gemini CLI and 3 pro was great for few weeks and now it's worse than 3 flash or any smaller model from competitor which are ra…

  10. comment
    Comment #47075757

    Looks great!

  11. comment
    Comment #47075725

    Great model until it gets nerfed. I wish they had a higher paid tier to use non nerfed model.

  12. comment
    Comment #47075689

    I hope to have great next two weeks before it gets nerfed.

  13. story
  14. story
  15. comment
    Comment #45971667

    Tried Antigravity for 2 queries and my model quota limit breached. Model definitely felt better than GPT 5.1 (my current daily driver). I am continuing to use Gemini 3 Pro on Curso…

  16. comment
    Comment #45965676

    NPM also seems to be down due to this! https://status.npmjs.org

  17. comment
    Comment #45853967

    It’s a full fledged tool like DataDog which is opensource and can be selfhosted. You can replace honeycomb with it. What features do you think it’s missing compared to honeycomb?

  18. story
  19. story
  20. comment
    Comment #45691590

    Discovered this while I was researching about why some LLM models perform significantly worse at times. I have experienced this more with Claude.

  21. story
  22. comment
    Comment #45665277

    “We’re relying a lot on Alibaba’s Qwen model. It’s very good. It’s also fast and cheap,” he said.

  23. story
  24. story
  25. comment
    Comment #45634899

    It’s possible with this extension: https://chromewebstore.google.com/detail/unhook-remove-youtu... I use it on firefox