Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: AskHN

patterns.app

Post reply on HN
Print view View original

101–110 of 139 posts

Re: Show HN: AskHN

#101

Post by leobg »

I like the project. Had been wanting to do this myself for a long time, because HN has become the first place I go to nowadays for answers, and I value the intelligence and experience distilled in the comments here.

I do not like that it seems to be effectively an ad.

> Embedding every single one of the 6.5 eligible comments was prohibitively time-consuming and expensive (12 hours and ~$2,000).

Does anybody understand what he’s talking about here? Assuming 6.5 million comments and an average token length of 70 we'd be looking at $180 ($0.0004 / 1K tokens).

Re: Show HN: AskHN

#102

Post by gus_massa »

blueicelake121 wrote: post #85

[flagged]

It looks interesting, but posting it on random threads of HN will make users flag your post and mods ban your account.

The post definitively needs more info! Who are you? How do you pick the kids? Are you the "teacher", an "organizer" or just someone enthusiastic that is related to the project? Programing language? Age of the kids? Have you done something similar before? Length of the course? Why do you need money?

Try to write a long post answering all that questions and perhaps a few more, but not too long. Make a new post, and then make a comment explaining you are the [teacher or whatever], and be ready reply to the comments in the thread.

Some official suggestions in https://news.ycombinator.com/newswelcome.html

Re: Show HN: AskHN

#104

Post by ducktective »

flappysolutions wrote: post #91

I'm quite pleasantly surprised by this response: Question: what are the biggest fallacies of people that post on hackernews? Answer: One of the biggest fallacies of people that post on Hacker News is the nirvana fallacy, which is when someone jumps from "thing x is imperfect" to "thing x is worthless" without considering any of the benefits. People also tend to be familiar with certain technologies and will discount…

It kinda enumerated all possible characteristics of people and their approaches to technical issues, not something unique to HN.

Re: Show HN: AskHN

#105

Post by freeqaz »

jerpint wrote: post #65

Nice! We built something very similar recently, it is more like "Ask your documentation" but very similar implementations otherwise. See a demo on the huggingface transformers documentation: https://huggingface.co/spaces/jerpint/buster code: https://github.com/jerpint/buster

Starred! We've been looking to build something similar so I appreciate you sharing this here.

The only other project that I've seen that's doing something close to this is this one: https://github.com/getbuff/Buff

It's a bit more similar to the OPs bot (it's a Discord bit).

Cool to see momentum in this space!

Re: Show HN: AskHN

#106

Post by ysavir »

actually_a_dog wrote: post #78
vidarh wrote: post #67

Earlier quoted context omitted.

I wish the results were reversed, so I could "well actually" your comment, but 'site:news.ycombinator.com "well actually"' gives ca. 4k results in Google and 'site:news.ycombinator.com "I think you'll find"' gives close to 17k results, so you appear to be right.

Well, "it turns out that" beats both, with about 26k results ;)

I am mildly disappointed that none of the phrase pitches in this thread were phrased with the given pitch.

Re: Show HN: AskHN

#107

Post by danuker »

notahacker wrote: post #99
danuker wrote: post #47

Earlier quoted context omitted.

Yeah, to me it looks like the learning rate was way too low to make a difference. I don't see any of the sublime and succinct snark.

Yeah. Also full of GPT-3isms like "ultimately the choice ... comes down to the specific project and its ... requirements" and not nearly contrarian enough A bot focused on the output of HNers would insist on providing arguments against going through Google's interview process in the first place and suggestions that the correct answer to "Python or R" should be Haskell or Julia and would never suggest prioritising emo…

Thank you for the laffs =)

Re: Show HN: AskHN

#108

Post by shanusmagnus »

setgree wrote: post #88

As is often true of GPT responses, there's some nonsense interspersed here, e.g. the claim that R has "a more mature package universe" than Python. I think this is false, but if you're reading quickly, it sounds cogent enough. As Sarah Constantin observed about GPT2 [0]: > if you skim text, you miss obvious absurdities. The point is OpenAI HAS achieved the ability to pass the Turing test against humans on autopilot..…

I wonder if the "default to humility" heuristic probably does more harm than good on net, because the people who heed it probably shouldn't, and the ones who should won't.

Re: Show HN: AskHN

#109

Post by ux-app »

setgree wrote: post #98
leereeves wrote: post #95

Earlier quoted context omitted.

> there's some nonsense interspersed here, e.g. the claim that R has "a more mature package universe" than Python. As a programmer, I find R hard to use and not very well designed, so I can see why you'd call that nonsense. But when I was a math student, I found that in some ways R does have "a more mature package universe". There were many math algorithms that I could find packages for in R and not in Python, even a…

Absolutely, for statistics and visualization I think R and its packages are (sometimes) superior. But GPT responses don't generally offer those kinds of nuances; the claim is that the packages are "more mature," period. And it's for good reason that the _most_ mature Python packages, e.g. numpy and pandas, are used by data scientists in production pretty much everywhere.

amazingly, your comment will eventually be added to the CHatGPT corpus and at some point down the line may be used to add the nuance that's currently lacking :)

Re: Show HN: AskHN

#110

Post by GreenWatermelon »

heleninboodler wrote: post #79
bityard wrote: post #14

Earlier quoted context omitted.

If it's really trained exclusively off of HN comments, I expect most of the bot's responses will evade the actual question but spend several paragraphs debating the factual specifics of every possible related tangential point, followed by an thinly-veiled insult questioning the user's true motivations.

In no way does a typical HN comment debate every possible related tangential point. Do we expect a modicum of intellectual rigor? Yes. But to say every tangent is followed and scrutinized is simply factually untrue. And several paragraphs? I challenge you to show even a large minority of argumentative responses that veer into "several" paragraphs. You characterize this as "most of the ... responses" but I think that'…

This is my favorite type of humour.
Post reply on HN