Live data from Hacker News

Viewing profile — hectormalot

hectormalot

HN member
Joined
Fri, Dec 28, 2012, 9:32 PM UTC
HN karma
1,231
Public activity
298 items

About hectormalot

Building the best AI for phone-based customer service at Stellar (http://www.stellarcs.ai). I'm a self taught programmer (Ruby, Go, Python, TS, Rust) with a background leading teams across consulting and banking before Stellar.

dennis@stellarcs.ai

Recent public activity

  1. comment
    Comment #49086331

    I’m not sure it will go this direction. Using a generic (near) frontier model is often cheap enough that you need to talk really big volumes before it pays off to fine tune. My exa…

  2. comment
    Comment #49069213

    Likely a lot of those tokens are cached. And because it’s an individual project it’s likely this is under a personal Claude Max 20x plan.

  3. comment
    Comment #48374395

    Ah my mistake, I thought he was making a broader point that other providers always have deep subprocessor stacks.

  4. comment
    Comment #48369590

    We have a vendor with almost no subprocessors because they run their own hardware in a colo. It is refreshing actually. They can accurately answer questions on how everything works…

  5. comment
    Comment #48349383

    The thing that surprises me is they flew back to Newark for almost 90 minutes. It doesn't make sense to me. (1) Either you believe the threat is credible and you put it down at the…

  6. comment
    Comment #47992313

    Thanks, appreciate the details. 99% is far above the amount I expected, and if it specifically hits hard to cache data then I can see how that brings a system to its knees.

  7. comment
    Comment #47992279

    Thanks. I imagine there is a (a) a lot of interest in scraping source code, and (b) many requests to forges hitting expensive paths. 99% of volume though, wow, much more than expec…

  8. comment
    Comment #47990105

    Maybe I’m naive about this, but I didn’t expect AI scrapers to be that big of a load? I mean, it’s not that they need to scrape the same at 1000+ QPS, and even then I wouldn’t expe…

  9. comment
    Comment #47984711

    Stellar | Amsterdam, the Netherlands | Onsite (2 days remote OK) | €70-100k + equity | https://stellarcs.ai Hey, I'm one of Stellar's founders. We're building AI for large contact …

  10. comment
    Comment #47604566

    Stellar | Amsterdam, the Netherlands | Onsite (2 days remote OK) | €70-100k + equity | https://stellarcs.ai Hey, I'm one of Stellar's founders. We're building AI for large contact …

  11. comment
    Comment #47507818

    Indeed. Similar accident (USAir 1493/Skywest 5569) shows that thinking exactly.[1] Was easy to pin on the controller, they went far beyond that in their analysis. Almost always imp…

  12. comment
    Comment #47296141

    There’s both a quality and quantity angle. For some work, similar to the philosophy example of GP, LLMs can help with depth/quality. Is additive to your own thinking. -> quality ap…

  13. comment
    Comment #47209645

    Datapoint: I’m running nightly now because the latest 1.2 release has a known crash-on-wake bug when disconnecting an external monitor. Accordingly the issue tracker it was fixed m…

  14. comment
    Comment #47130068

    We're doing a lot with the realtime models. Happy to see a new release. Initial feel from a few calls is that it seems to perform better with alphanumeric inputs. Voice seems consi…

  15. story
  16. comment
    Comment #47111727

    SQLC for me has been able to replace most cases of use an ORM for. It made most of the boilerplate of using plain SQL go away, I get type safe responses, and it forces me to be mor…

  17. comment
    Comment #46686004

    > So, what's your trick to avoid getting skipped Ideally write the hiring manager and not HR. And, write something that makes it hard to not want to talk to you. 1: Minimal hygiene…

  18. comment
    Comment #46606227

    Context: I’m in the Netherlands. With taxes, power is around 25cent/kWh for me. For reference: Amsterdam is around a latitude of 52N, which is north enough that it only hits Alaska…

  19. comment
    Comment #46384306

    Thx, forgot to double enter.

  20. comment
    Comment #46382876

    Im in this business, and used to think the same. It turns out this is a minority of callers. Some examples: - a client were working does advertising in TV commercials, and a few pe…

  21. comment
    Comment #46172174

    > On the other hand, if each service experiences the same hour per year of downtime but at different times, then the person is likely to be blocked for closer to 100 hours per year…

  22. story
  23. comment
    Comment #45786360

    As I was typing this it came to mind. Will test against one of my own servers one of these days to confirm.

  24. comment
    Comment #45786258

    I have 1Gbit at home, but almost never reach those speeds when downloading games. It’s one of those cases where it makes sense (I want to play now!), but I’m under the impression t…

  25. comment
    Comment #45265594

    Partly, I did the electrical work myself (dug a cable to the shed, added a breaker, etc). Asked the installer to put the panels on the roof and connect it to the existing line. The…