Live data from Hacker News

Viewing profile — tingletech

tingletech

HN member
Joined
Sat, Dec 18, 2010, 5:42 AM UTC
HN karma
2,386
Public activity
817 items

About tingletech

http://tingletech.tumblr.com/

[ my public key: https://keybase.io/tingle; my proof: https://keybase.io/tingle/sigs/sUg3nhBMyAmDusnRiGy2z6Fgzxj9Woonpb5oRwQSxzg ]

Recent public activity

  1. comment
    Comment #49210665

    I think the author is distributing a web app that is run by hobbyists with a lot of esoteric home labs?

  2. comment
    Comment #49186488

    you have to have either a tall viewport or scroll to the bottom of the page

  3. comment
    Comment #49186462

    When I tried to sign up for Qwen last month (after getting an ad on youtube), after entering my credit card for a "free" trial, Alibaba wanted me to upload a picture of my driver's…

  4. comment
    Comment #49124676

    That's what is seems to say in the article

  5. comment
    Comment #49060735

    Depends on your rules of order. Under Robert's you can have multiple seconds but seconds aren't recorded. In model UN there are multiple seconds. Second'ing a motion is not general…

  6. comment
    Comment #49028624

    my grandpa had a table top model of a beam engine that he would power with a pressure cooker

  7. comment
    Comment #49027353

    What does the patent and trademark office have to do with the copyright office at LoC? I agree that the copyright office has not said this either -- they have just said that you ne…

  8. comment
    Comment #49016489

    the grammar support/json-schema applies to a whole response, but I was under the impression a similar logit guide rail can be applied when a tool call is opened.

  9. comment
    Comment #49014514

    it works quite will for me in llama.cpp, but I get more like 20% to 40% speedup on tokens per second. I generally use spec-type = draft-mtp,ngram-mod spec-draft-n-max = 4 I have no…

  10. comment
    Comment #48920858

    I thought they got like a logit mask that removes illegal next tokens, at least in llama.cpp and GBNF.

  11. comment
    Comment #48909942

    depending on the age of the children, could it be designed this way for people who are not allowed to access the internet generally, but their parents will let them have the app in…

  12. comment
    Comment #48864828

    The comments are not showing up for me now, but when they were still showing for anonymous users, there was a link to https://commoncrawl.org . I've been sort of worried about lett…

  13. comment
    Comment #48818628

    I had just never heard of it before, I didn't realize it was well know. I was quoting from it's specification.

  14. comment
    Comment #48818508

    In the context of the title of the hn submission, I read “RAG Context” as “the retrieved content injected into the context window” .... "read" read /rε d/ not /riːd/ > So when an a…

  15. comment
    Comment #48812326

    I read “RAG Context” as “the retrieved content injected into the context window”

  16. story
  17. comment
    Comment #48811868

    "Standard ML is a functional programming language, in the sense that the full power of mathematical functions is present." From a Pdf linked on the repo (I didn't know what Standar…

  18. story
  19. comment
    Comment #48793879

    I just googled it a second ago https://martinfowler.com/articles/codemods-api-refactoring.h...

  20. comment
    Comment #48776080

    Google ships a local LLM with chrome browser nowadays. Don't they also provide the weights for the LLM built into iOS and MacOS?

  21. comment
    Comment #48709092

    You could also produce special purpose applications this way, say to provide access to the online library catalog, or a run a gopher client for use in a public terminal lab. Telnet…

  22. comment
    Comment #48708474

    When I was an undergraduate biology student in 1991 a suitemate told me I should go to some desk in some building over by Muir and get an account on the VAX. There were strange roo…

  23. comment
    Comment #48588098

    I do think it pays to be nice to the model. When the context window is running out I like to ask "please summarize what went well and what didn't work in this session. How could th…

  24. comment
    Comment #48477666

    that article seems to suggest 20TB total over the dozen deployments in prod.

  25. comment
    Comment #48328814

    Why would a model know that one washes cars at a car wash? We don't clean our bodies at the body wash or clean the kitchen at the kitchen wash.