Live data from Hacker News

Viewing profile — adaboese

adaboese

HN member
Joined
Fri, Oct 27, 2023, 6:45 PM UTC
HN karma
129
Public activity
106 items

About adaboese

Building aimd.app. Ask me anything about content generation!

Recent public activity

  1. comment
    Comment #43164095

    Hilarious!

  2. story
  3. story
    Ask HN: Has anyone developed a single API endpoint to access all LLMs?

    I wish there was a way to query OpenAI, Groq, etc. all using single API endpoint. Has anyone built an abstraction that lets do it?

  4. comment
    Comment #39597679

    Image inputs (prompts) are generated with respective models, but the actual images are generated using DALLE.

  5. comment
    Comment #39597671

    Forgot to mention, Claude appears to be a lot more rate-limited that OpenAI. Hit quite a few concurrency rate limits, but as long as you have auto-retry, it is non-issue.

  6. story
    Claude vs. OpenAI GPT-4 generated content, side-by-side comparison

    - OpenAI GPT-4 https://gist.github.com/adaboese/12e3c3d28783bc831c202ad1e55d932b - Claude 3 (Opus) https://gist.github.com/adaboese/d0b7397381726a7d394920e6a82ee39c Both of these a…

  7. story
    Ask HN: The "Routing deadline expired" error

    I am not even sure where to ask this, but I am at the end of my wits trying to identify the source of an error. My app users are receiving error "Routing deadline expired" I am als…

  8. story
  9. comment
    Comment #39323146

    Just use a dedicated tool. It is not that hard. If you want higher level abstraction, you have a whole spectrum of next gen queues, like Temporal, Trigger.dev, Inngest, Defer, etc.…

  10. comment
    Comment #39322950

    Postgres is extremely expensive to scale. Why on Earth would you try to put queue there.

  11. comment
  12. story
  13. story
  14. comment
    Comment #39293629

    For anyone who is looking for UI library that's compatible with Panda, I highly recommend https://park-ui.com/ By far the most polished and actively developed. I am building a seco…

  15. story
    Sensible "Safe-Password" Checks

    Recently I had an incident where a user reported that their account was hacked. It turned out that they've used their email (the same email they've used to sign up) as their passwo…

  16. comment
    Comment #39199274

    commute sucks regardless of the team size, no denying. I am only referring to whether work in the office can be rewarding or not

  17. story
  18. comment
    Comment #39196854

    I am a bit advocate of remote work, but I actually think for _small teams_ offices make sense. I would thoroughly enjoy working in 4-8 people small office. It is when you get into …

  19. story
  20. comment
    Comment #39121093

    There are a ton of SEO optimizations that are extremely significant: * performance/SSR * interlinking/dead links * keyword cannibalization to name a few

  21. comment
    Comment #39119011

    The annoying thing about this is that it will ruin this feature for everyone else. I, and many others, use this for requesting to index time sensitive content.

  22. comment
    Comment #39112044

    Just for fun, I just tested a few recently generated articles with https://huggingface.co/spaces/tomg-group-umd/Binoculars (someone linked it in this tread) and it ranked them as "…

  23. comment
    Comment #39112029

    To clarify, the style experiment I've referenced earlier was just that – an experiment. I did not implement those methods into my software. Instead, I focused on how to eliminate t…

  24. comment
    Comment #39111989

    I use https://originality.ai/ as the benchmark. I've tested all commercially available services, and Originality (at the time; its been a few months) provided the lowest false-posi…

  25. comment
    Comment #39111936

    I will also add that, at least for now, if you are doing it for SEO, it _really_ doesn't matter. I was planning to make a case study benchmarking my algo against a bunch of other c…