Live data from Hacker News

Viewing profile — vincirufus

vincirufus

HN member
Joined
Sun, Nov 10, 2024, 11:14 AM UTC
HN karma
184
Public activity
43 items

About vincirufus

Spend a lot of time trying to get my AI Agents to behave nicely.

Recent public activity

  1. story
  2. story
  3. story
  4. story
  5. comment
    Comment #45238706

    This could be game changing

  6. comment
    Comment #45235152

    very interesting where can i read more about Diffusion based LLMs, I did try asking dllm to explain itself and it did ok :-)

  7. comment
    Comment #45235140

    this could be a game changer for the agentic era, similar to what online payments did to the ecomm & online banking era

  8. story
  9. story
  10. comment
    Comment #45159645

    Yup exactly!! its a subtle change happening under the hood, When people have a good interaction with ChatGPT they attribute it to the LLM, but in most cases, its the agentic featur…

  11. comment
    Comment #45159579

    I stumbled upon this old post when researching on the best ways for my ai agent to maintain notes about our interactions. Applies to humans as well

  12. story
  13. comment
    Comment #45159308

    Well there was is a lot of human element and infact this post was an output of conversations with different people talking about LLM and ChatGPT. I guess Claude over did the 'fix g…

  14. comment
    Comment #45159266

    Sadly I don't have a Claude subscription for the number of tokens needed for Opus. Although I'd admit I used Sonnet to clean up and improve the language and grammar.

  15. comment
    Comment #45159237

    It used to be a thin wrapper, but todays chatGPT is closer to an agent

  16. story
  17. comment
    Comment #45146012

    update the title to not seem biased / hyped

  18. comment
    Comment #45145999

    feedback accepted got rid of the killer bits

  19. comment
    Comment #45145992

    Well I'd call them the poor person's claude code, wouldnt compare it with Opus but very close to Sonnet and Kimi

  20. comment
    Comment #45145985

    Ahh bugger I pasted the wrong link I had this one open in another tab..

  21. comment
    Comment #45145970

    yeah I too have heard similar concerns with Open models on OpenRouter, but haven't been able to verify it, as I don't use that a lot

  22. comment
    Comment #45145467

    Yup. I think it was a nice honest and vulnerable thread

  23. story
  24. comment
    Comment #45101116

    may the title of this should say Next.js middleware /logging is infuriating

  25. comment
    Comment #45093440

    There is already a growing number of people who use tools like super whisper to interact with agents. At work I'm building a "chief of staff" kind of a voice agent where you simply…