Live data from Hacker News

Viewing profile — KHRZ

KHRZ

HN member
Joined
Sat, Feb 26, 2022, 3:46 PM UTC
HN karma
101
Public activity
54 items

About KHRZ

No profile information was provided.

Recent public activity

  1. comment
    Comment #49025147

    I already am managing Unity from my terminal, using Codex. Although one issue is that PowerShell + C# reflection gets flagged as malware by Windows Defender.

  2. comment
    Comment #48707081

    How would it prevent an agent from writing a script that discovers the secret file? It's not magic.

  3. comment
    Comment #48677169

    They also shut down Ryujinx at the same time by simply pressurimg the creator. So it was just an excuse they used.

  4. comment
    Comment #48620361

    This is the biggest lesson I got from LMMs. I have a 1 million LOC vibe coded project that I can only imagine would fit in a few hundred thousand lines. But it's still holding up, …

  5. comment
    Comment #48216290

    If that's in API price, they may be better of with the subscription.

  6. comment
    Comment #47701867

    I don't think the bug is anything special, just another confusion the model can make from it's own context. Even if the harness correctly identifies user messages, the model still …

  7. comment
    Comment #47188851

    DeepSeek would print all it's mental gymnastics to censor itself in the reasoning phase directly to the user, before shutting down the conversation. Apparantly such an odd move is …

  8. comment
    Comment #46218881

    General Intelligence has already been demonstrated to be possible by the human brain, so I don't really get how physicality is an argument against AGI. Who is to say biological com…

  9. comment
    Comment #46183393

    LLMs can actually make up for their negative contributions. They could go through all the references of all papers and verify them, assuming someone would also look into what gets …

  10. comment
    Comment #45062793

    I was curious what kind of company needed to develop all these different kinds of advanced tech. Turns out it's just so they can be sneaky and trade shares quickly. Kind of sad IMO…

  11. comment
    Comment #44403071

    We just entered the era where LLMs could mine his gems for him though.

  12. comment
    Comment #43946705

    You have been a bad user. Bing has been a good Bing.

  13. comment
    Comment #43899985

    You can literally today prompt ChatGPT with API instructions to drive a car, then feed it images of a car's window outlooks and have it generate commands for the car (JSON schema r…

  14. comment
    Comment #43705415

    At least they had trials back then. Switch emulators last year simply got intimidated to abandon their projects.

  15. comment
    Comment #43580561

    There was another concept trying to operate on a logical view of the world, called copyright. It tried to establish a few simple rules, with the goal to promote art and science. Ho…

  16. comment
    Comment #43215756

    Those Russians have their own government to blame, which in addition to stealing Ukrainian land has stolen assets of Western companies, including billions in planes. They are legit…

  17. comment
    Comment #42893862

    With many people too lazy to read 2 walls of text, a lot of picks might be random.

  18. comment
    Comment #42863622

    Look up the Streisand effect.

  19. comment
    Comment #42863610

    Prisoners?

  20. comment
    Comment #41922111

    YouTube literally allows trading scams into their ad program, which they force onto users through their terms of service. This is far worse, as naive users may think that YouTube h…

  21. comment
    Comment #41922078

    In Minesweeper you also win when all non-mine tiles are revealed.

  22. comment
    Comment #41543770

    One good use case is unit tests, since they can be trivial while at the same time being cumbersome to make. I could give the LLM code for React components, and it would make the te…

  23. comment
    Comment #41489211

    Just take 10% of the Russian war economy to clean the garbage patch, then we would have double the money fro Ukraine weapon savings!

  24. comment
    Comment #41020762

    That's a lot of thinking they've done about LLMs, but how much did they actually try LLMs? I have long threads where ChatGPT refine solutions to coding problems. Their example of l…

  25. comment
    Comment #41007798

    From what I heard Crowdstrike just updated their DB file, which means the bug was alreadyq there, waiting for someone to trigger it with a "low risk" quick roll out.