Plato Education

Learning and science

ai-generated explainers

SHOW HN2023

61points
30comments
#952of 3,109 in 2023
Top 31%of 2023 by points

How HN took it

RoastedHalf or more of the comments are critical

3 positive, 4 neutral or asking, 0 mixed, 7 critical, out of 14 comments about the project. Thread score -0.21.

Execution: 0 for, 5 againstIdea: 3 for, 2 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

  • Useful for learning unfamiliar topics and seeing what to explore

    From 3 comments
    • Valid point, however, I personally believe that the questions generated hold greater significance as they provide direction in terms of what to explore in a particular subject…
      Mamadou_H on HN
    • this particular use of LLM could prove helpful in the sense that it shows you what to look for in a given subject matter. The generated answer can easily be verified.
      Mamadou_H on HN
    • This is freaking sick! Really cool use of ai to democratize higher level education.
      MrLaheyyy on HN

Objections

  • Generated content can't be trusted without verification

    From 3 comments
    • Sounds like you reinvented Wikipedia's "Simple English" pages, but in a way that can't be trusted very much.
      amelius on HN
    • If you don't have any background in a topic, then how do you know it is getting it right? You don't know enough to know if you can trust any given response. Either you have to…
      humanistbot on HN
    • Yeah, no kidding. This is what LLMs are not meant for 101 -- it'll get a lot right, a solid amount of the time (spare me the anecdotes), but the idea that someone who doesn't…
      thenberlin on HN
  • Recommending LLMs as a knowledge source is a bad use

    From 1 comment
    • Big agree. It feels wrong to dissuade someone from building something, this is likely an exercise in creativity, but I have to say this goes on my "Bad Use of LLMs" list. Sure,…
      jszymborski on HN
  • Sudoku explanation looked inaccurate

    From 1 comment
    • First page I clicked was the Computer Science...Sudoku page. Really?: At each step of the recursion, you try out all of the available options, and as soon as one of them leads to…
      empdee on HN

Requests

  • Add references or sources, like Bing Chat

    From 1 comment
  • Re-ask questions periodically and keep answer versions

    From 1 comment
    • I think it would be interesting if you periodically re-ask the same question maybe even to different AIs and keep all versions of answers accessible so its possible to see the…
      gagabity on HN

Questions

  • What prompt was used?

    From 1 comment

Alternatives named

  • Wikipedia Simple English pages

    From 1 comment
    • Sounds like you reinvented Wikipedia's "Simple English" pages, but in a way that can't be trusted very much.
      amelius on HN
  • Oxford Very Short Introductions

    From 1 comment
    • For a similar idea, but human-generated (by leading experts in the respective fields), I can recommend the Very Short Introduction series by Oxford University Press.…
      globalise83 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/35394553)