Live data from Hacker News

Viewing profile — crakhamster01

crakhamster01

HN member
Joined
Wed, Mar 06, 2019, 7:18 PM UTC
HN karma
408
Public activity
148 items

About crakhamster01

No profile information was provided.

Recent public activity

  1. comment
    Comment #49118953

    Having also worked with the tools you mentioned, is using commits in-place of "versions" + squash merging all that different? 1. Adding commits means reviewers can easily diff chan…

  2. comment
    Comment #48993385

    > I know personally the value the LLM adds to my workflow is considerably more than the $200/m I pay the frontier labs. AFAIK the frontier labs make their money on enterprise, and …

  3. comment
    Comment #48544361

    Thanks for sharing! I make videos and often have the same problem as well. Being able to semantic search over your library is useful, but does it solve the review problem? I feel l…

  4. comment
    Comment #48456300

    I don't really understand how engineers at Uber are hitting $1500/month. Are they forced to pay API costs? My company provides employees with API keys and soft limits, but as soon …

  5. comment
  6. comment
    Comment #48305503

    > As further evidence that enterprise agents represent product-market fit for these companies, consider their open job listings. PMF is one interpretation, but it could also be rea…

  7. comment
    Comment #48204789

    > Antigravity also offers models other than Gemini as well. When you say Antigravity, you think of a platform whereas when you say Gemini you think of the model. I the other reason…

  8. comment
    Comment #48204577

    > I would wager your feelings conflict with their analysis How their target audience feels isn’t separate from “analysis” - it’s the input.

  9. comment
    Comment #48203833

    How does anyone internally at Google justify these decisions? Even if there are competing implementations, in terms of brand recognition, I feel like “Gemini” is more closely assoc…

  10. comment
    Comment #47987424

    I realize this post is about the pelican test, but in regards to coding, has anyone tried out the advisor strategy with V4?[0] e.g. Have V4 call out to Opus when it's uncertain, bu…

  11. comment
    Comment #47922981

    I read the piece before coming to the comments and had a similar feeling as OP - hence my comment. If AI wasn't used then my apologies, I didn't mean to diminish your work. I agree…

  12. comment
    Comment #47920879

    Pasted it into Pangram AI and it classified the article as 100% AI generated, so take that as you will...

  13. comment
    Comment #47907871

    The app looks very slick! Just read through the docs and a couple of the Looms. This might be a dumb question, but what are people using these MD knowledge bases for? What has this…

  14. comment
    Comment #47690549

    This was a great comment. I don't know if it's common knowledge, but this really helped clarify how the shift happens. I also remember half coding and half prompting a few months b…

  15. comment
    Comment #47591312

    > One thing we know for sure is LLMs write code differently than we do. Kind of. One thing we do know for certain is that LLMs degrade in performance with context length. You will …

  16. comment
    Comment #47376796

    I can maybe see this argument being valid for OSS - as Carmack says, by nature it should be "no strings attached". I don't think that's all anti-AI activists care about though. Hon…

  17. comment
    Comment #47324303

    The wave of LLM-style writing taking over the internet is definitely a bit scary. Feels like a similar problem to GenAI code/style eventually dominating the data that LLMs are trai…

  18. comment
    Comment #47320123

    I had a similar reaction to OP for a different post a few weeks back - I think some analysis on the health economy. Initially as I was reading I thought - "Wow, I've never read a f…

  19. comment
    Comment #47089510

    > taste scales now. Not having taste also scales now, and the majority of people like to think they're above average. Before AI, friction to create was an implicit filter. It meant…

  20. comment
    Comment #46643936

    I think this advice is pretty apt for small to medium sized companies. We're all invested in the company succeeding, but you don't want to become known as the person that always sa…

  21. comment
    Comment #46575705

    I feel like both of these examples are insights that won't be relevant in a year. I agree that CC becoming omniscient is science fiction, but the goal of these interfaces is to mak…

  22. comment
    Comment #45820347

    It's funny that you mention moving outside the city when Zohran's tax plan is centered on bringing the corporate tax rate in-line with our neighboring state. I'll also caveat that …

  23. story
    Ask HN: How do you measure "AI slop"?

    Recently, my employer has been pushing hard for LLM adoption across eng, with an expectation of increased productivity. Eng has followed suit, and as a result I've been getting a l…

  24. comment
    Comment #44743618

    > and now, what screen you’re on, what do you see? There's a "follow me" feature to see what other users are doing. It's been around for several years.

  25. comment
    Comment #44540159

    There's undoubtedly a cohort of tourists that come to Japan with the "Disneyland" mindset, and I agree that some sort of government-level change is needed to curb abuse. But I woul…