Live data from Hacker News

Viewing profile — shepherdjerred

shepherdjerred

HN member
Joined
Sun, Jun 09, 2019, 8:13 PM UTC
HN karma
5,463
Public activity
2,460 items

About shepherdjerred

https://sjer.red

Recent public activity

  1. comment
    Comment #49225422

    OpenAI has a pretty clear definition of AGI > OpenAI’s mission is to ensure that artificial general intelligence (AGI)—by which we mean highly autonomous systems that outperform hu…

  2. comment
    Comment #49213116

    OK I’ll take the bait. Were devs supposed to optimize RAM for a shortage that might come? I’m guessing you had enough foresight to stockpile RAM?

  3. comment
    Comment #49177816

    https://theonion.com/sam-altman-if-i-dont-end-the-world-some...

  4. comment
    Comment #49164967

    IMO the key thing is that interviews have a heavy component of randomness. The question your interviewer selects (both topic and difficulty), how the interview performs as far as p…

  5. comment
    Comment #49164776

    when someone describes a static site/app they generally mean there is no backend. not that the frontend is a static image for example you can service static sites from S3 that have…

  6. comment
    Comment #49164664

    Wow, I am not sure that I want my safety app to be videcoded by someone without experience

  7. comment
    Comment #49149521

    Ebay sucks but I'm not sure there are any better options in the states

  8. comment
    Comment #49149512

    Isn't this almost certainly in the training set?

  9. comment
    Comment #49131329

    So this is one interface that can render to multiple charting backends? If AI is writing the "Flint", why not just have it write the backend code instead? I'm not sure why I would …

  10. comment
    Comment #49131240

    The goal of that project wasn’t to produce a web browser, it was to market Cursor

  11. comment
    Comment #49130708

    Conversely, it has never been more feasible for alternative web browsers to be created and maintained outside of big tech.

  12. comment
    Comment #49130631

    I wonder if we'll see LLM elevator scheduling

  13. comment
    Comment #49125772

    You’re not alone! I love Java too. It is excellent. I don’t reach for it much anyone since I prefer TypeScript’s type system and the ability to use the same language for both clien…

  14. comment
    Comment #49118505

    Summarization of datasets, categorization

  15. comment
    Comment #49092119

    Is this useful for pentesting existing systems/infra, or is it only useful for a "review my project for bugs"?

  16. comment
    Comment #49087509

    I loved this! The article was written in such an approachable way for someone less familiar with microbiology

  17. comment
    Comment #49086747

    27 is a lot better. You can make the UI opaque again (they provide a transparency slider)

  18. comment
    Comment #49086585

    I think the key part of the parent was talking about disabled individuals. I don’t think anyone is advocating to provide a free ride for capable individuals Of course someone has t…

  19. comment
    Comment #49079949

    I found this: https://artificialanalysis.ai/agents/coding-agents#harness-c... I don't think it's very good though. As an example I can use one CC instance to delegate to several to…

  20. comment
    Comment #49079937

    I am not sure -- Anthropic probably does benefit from the vertical integration here. They can train their models to work better with CC, which isn't really an option for third part…

  21. comment
    Comment #49079422

    I’ve enjoyed using Kimi K3. The biggest issue for me so far is finding a good harness. Claude Code is excellent for tasks that require backgrounding processes/agents, or fanning ou…

  22. comment
    Comment #49078570

    I think the point you're trying to make is that you can always make your exposed surface area smaller But that, of course, is not going to survive contact with reality

  23. comment
    Comment #49073647

    IMO this points to two things: - You didn't have the agent plan and de-risk/experiment beforehand - You didn't glance at the output Working with agents is not very different from w…

  24. comment
    Comment #49073403

    This is such a good explanation of OOP vs DOD

  25. comment
    Comment #49063409

    > Ask yourself, where are we spending our energy right now as a species? Hey Claude, enter plan mode