Live data from Hacker News

Viewing profile — faxmeyourcode

faxmeyourcode

HN member
Joined
Thu, Jan 21, 2021, 4:17 PM UTC
HN karma
540
Public activity
128 items

About faxmeyourcode

Software engineer in Arkansas

Send me an email!

john@ouachitalabs.com

https://linkedin.com/in/jomccr https://ouachitalabs.com/ https://macrosforhumans.com

Recent public activity

  1. comment
    Comment #49212327

    Compaction, busting the cache, and other issues like that will lose significance when you're running at 15k tokens per second like chatjimmy. Very interesting to think about what w…

  2. comment
    Comment #49071062

    Apparently there was a gathering of harp guitarists here in North Little Rock at a guitar shop that recently opened just down the street from where I live last year: https://www.ha…

  3. comment
    Comment #49000279

    I've definitely noticed 5.6 sol being extremely trigger happy in ways other models, even 5.5, we're not. I would definitely categorize a few small incidents at work where it perfor…

  4. comment
    Comment #48632706

    I feel like another comparison worth looking at is purely cost. Capability per dollar is something I care about: Opus API $5/$25 Sonnet API $5/$15 Haiku API $1/$5 GLM 5.2 API $1.4/…

  5. comment
    Comment #48565399

    A town I grew up in went absolutely crazy with roundabouts over the last 10 years or so. They built them everywhere. Most are pretty straightforward and they simplify traffic a ton…

  6. comment
    Comment #48549723

    I work a lot with databases, but only a couple times have I really messed with time series stuff. I've enjoyed reading your list of tricks and it's gotten me interested in playing …

  7. comment
    Comment #48415053

    Somebody else in the thread brought up the benefit of snapshotting a database at a point in time stores not only the state of execution but also the code, etc. That is a unique ben…

  8. comment
    Comment #48414709

    I aggree - I'm not understanding the value of the project either if you look at the example here https://github.com/microsoft/pg_durable/blob/main/examples/i... It's an interesting…

  9. comment
    Comment #48414641

    This feels like the wrong solution to an age old problem solved by the DAG schedulers like Apache Airflow for a while now. Why would I want to store my control flow in the database…

  10. comment
    Comment #48309906

    I had a hunch that opus 4.7 hedged more than other models - and it turns out it's true model total_claims hedged_count hedged_pct claude-opus-4-7 1000 451 45.1 sonar-pro 1000 391 3…

  11. comment
    Comment #48048028

    An HP 50g was my calculator of choice, and the whole RPN style really rubbed off on me. Plus it had more advanced symbolic algebra capabilities than a ti83 equivalent. I enjoyed le…

  12. comment
    Comment #47879638

    How does it compare to mythos?

  13. comment
    Comment #47493598

    Wow, I didn't realize some RFID could reach 15 feet out - that's good to know. I naively thought you essentially had to be touching the surface of the tag.

  14. comment
    Comment #47324409

    If you treat LLMs as generic transformers, you can fine tune with a ton of examples of input output pairs. For messy input data with lots of examples already built, this is ideal. …

  15. comment
    Comment #47250644

    Especially for super constrained applications. I don't care if the language model that I use for my extremely specific business domain can solve PhD math or remember the works of S…

  16. comment
    Comment #47250531

    Labeling or categorization tasks like this are the bread and butter of small fine tuned models. Especially if you need outputs in a specific json format or whatever. I did an exper…

  17. comment
    Comment #47235247

    > Filip also told me that he asked Claude to continue on the even case after the odd case had been resolved. “But there after a while it seemed to get stuck. In the end, it was not…

  18. comment
    Comment #47170708

    Yea, I agree. The dataset is https://duckdb.org/2025/05/19/the-lost-decade-of-small-data

  19. comment
    Comment #47161799

    Neel, this is really cool. How long have you been working on this, and where did you guys get inspiration from? Did you work on vlms earlier or something like that? Just curious. A…

  20. comment
    Comment #46946439

    I love the idea behind MyVisualRoutine as a father with a disabled kiddo, thanks for sharing. The app is beautiful - much better than I could build - what tech is it using if you d…

  21. comment
    Comment #46945942

    Love this. An example of complete and total dominion over the machine. Great quote here too lol > Prometheus stole fire from the gods and gave it to man. For this he was chained to…

  22. comment
    Comment #46913155

    Everybody is different, I simply cannot stand the sight of chatgpt styled writing. Give me paragraphs.

  23. comment
    Comment #46806243

    I've lobbied to replace our internal tool with a django admin panel. I prototyped it and it showed that it would reduce our code by > 15k lines. Any internal webapps I need to buil…

  24. comment
    Comment #46765936

    One trick to get out of this scenario where you're writing a ton is to ask the model to interview until we're in alignment on what is being built. Claude and open code both have an…

  25. comment
    Comment #46765896

    > LLMs dont care about the story, they just care about the current state of the code You have to tell it about the backstory. It does not know unless you write about it somewhere a…