Autolabel

Data

data labeling library

SHOW HN2023

153points
22comments
#406of 3,109 in 2023
Top 14%of 2023 by points

How HN took it

CuriousMostly questions and neutral comments

2 positive, 6 neutral or asking, 0 mixed, 2 critical, out of 10 comments about the project. Thread score -0.06.

Idea: 1 for, 0 againstPrivacy: 1 for, 0 against

The thread, comment by comment

Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.

positive neutral or mixed critical about another commenter or something else the maker

What HN said

What people liked

  • Confidence estimation lets LLM labels be used where reliable and manual labeling for the rest

    From 1 comment
    • Thank you for open sourcing this! This seems very useful, especially because of the confidence estimation, which lets you use LLMs for the points they can do well and fall back…
      viswajithiii on HN
  • Support for self-hosted open-source models addresses privacy concerns

    From 1 comment
    • Yep! I totally understand the concerns around not being able to share data externally - the library currently supports open source, self-hosted LLMs through huggingface pipelines…
      nihit-desai on HN

Objections

  • OpenAI terms may forbid using outputs to build competing datasets or models

    From 2 comments
    • You should read carefully OpenAI terms and conditions before using it to build custom datasets.
      isawczuk on HN
    • For anyone wondering it's here https://openai.com/policies/terms-of-use: >use output from the Services to develop models that compete with OpenAI; Well, I still can use ChatGPT…
      iillexial on HN
  • Spamming HN with promotional posts

    From 1 comment
    • You just posted this here https://news.ycombinator.com/item?id=36384015 It's one thing to show HN / share, its another thing to spam it with your ads.
      voz_ on HN

Requests

  • Explain how confidence scores work

    From 2 comments
    • >Refuel provides LLMs that can compute confidence scores for every label, if the LLM you've chosen doesn't provide token-level log probabilities. How does this work exactly?
      msp26 on HN
    • How does the confidence scores work?
      applgo443 on HN
  • Support for llama.cpp self-hosted models

    From 1 comment
    • Yep! I totally understand the concerns around not being able to share data externally - the library currently supports open source, self-hosted LLMs through huggingface pipelines…
      nihit-desai on HN

Questions

  • What does it do that OpenAI function calling does not?

    From 1 comment
    • What can this do that the new ‘calling functions’ feature can’t? It seems to be roughly the same thing?
      bomewish on HN
  • Can data be used without sending it outside the organisation?

    From 1 comment
    • This is very interesting to me. We spent a significant time “labelling” data when I was in the public sector digitalisation. Basically what was done, was to do the LLM part…
      devjab on HN

Alternatives named

  • OpenAI function calling

    From 1 comment
    • What can this do that the new ‘calling functions’ feature can’t? It seems to be roughly the same thing?
      bomewish on HN
  • llama.cpp self-hosted models

    From 1 comment
    • You can self-host an open-source model. Llama CCP is a very popular project with great docs. https://github.com/ggerganov/llama.cpp You need to be careful about liscencing - some…
      oli5679 on HN

Category, keywords, summaries and labels on this page were made by AI (Thread Reader v2) and not checked by hand. Each point links to the comments it came from.

Add a badge to your READMEShown on HackerShow
[![Shown on HackerShow](https://hackershow.org/badge.svg)](https://hackershow.org/show/36409201)