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

LLMs are the ultimate demoware

blog.charliemeyer.co

Post reply on HN
Print view View original

51–60 of 128 posts

Re: LLMs are the ultimate demoware

#51

Post by Blackthorn »

baklavaEmperor wrote: post #49
getnormality wrote: post #21

Earlier quoted context omitted.

It's nice that you think it's clear and responsive, but I think it [1] needs to be validated by an expert in both the material and education. Or we need some way to show that people have actually learned the topic. People sometimes prefer explanations that are intuitive and familiar but not accurate. Meanwhile, there are math education resources like iXL that maybe cost a little money but the lessons and practice pro…

It’s interesting how people insist math requires expert validation when it’s literally the most self validating subject there is. The instinct to gatekeep even something as mechanistically checkable as algebra says more about insecurity in education than it does about rigor.

Wanting an actual check on the device that is notorious for making things up is gatekeeping now?

Re: LLMs are the ultimate demoware

#53

Post by lomase »

turnsout wrote: post #8

This is such a weak take to read while I have Claude Code running in the background creating a new database migration for a feature we're building

Can't your stack do that for you?

The one I use creates the migrations, locally, for free and deterministically in about 30 seconds.

Re: LLMs are the ultimate demoware

#54

Post by dingnuts »

tptacek wrote: post #7

It's wild to me that, of all the things to call LLMs out for, this piece has chosen to include math tutoring. I've been doing Math Academy for a bit over 6 months now, going from (essentially) Algebra II through Calc II (integration by parts, arc lengths, Taylor expansions) and LLMs have been a huge part of what has made that effective: * Clear explanation of concepts that respond to questions and reformulate when th…

Isn't this moving the goalposts? It's great that you're learning but MathAcademy appears to be a whole product that may incorporate an LLM but is much more, and it's a paid product none of us can evaluate. It's not possible to tell from looking at their site, or from your comment, what content is generated, or how it is verified before being used as teaching material.

There are probably smart ways to incorporate LLM output into an application like the one you're lauding but your comment is a little like responding "but my cake tastes good" to someone who says you shouldn't eat raw flour.

Re: LLMs are the ultimate demoware

#55

Post by badsectoracula »

dingnuts wrote: post #15
turnsout wrote: post #8

This is such a weak take to read while I have Claude Code running in the background creating a new database migration for a feature we're building

If Claude Code can do it what do we need you for?

What simonw wrote but also someone needs to ensure the code is correct and take the blame once it fails :-P.

I think even if we ever reach actual AGI (in the far far future), we'll still want low level meatbags around to blame :-P

Re: LLMs are the ultimate demoware

#56

Post by miltonlost »

simonw wrote: post #26
jdiff wrote: post #18

Earlier quoted context omitted.

Countless people in comments say this, but other people fail to see evidence of that in the wild. As has been said in response to this point many times in the past: Where's the open source renaissance that should be happening right now? Where are the actual, in-use dependencies and libraries that are being developed by AI? The only times I've personally seen LLMs engaged in repos has been handling issues, and they ma…

Let's look at every PR on GitHub in public repos (many of which are likely to be under open source licenses) that may have been created with LLM tools, using GitHub Search for various clues: GitHub Copilot: 247,000 https://github.com/search?q=is%3Apr+author%3Acopilot-swe-age... - is:pr author:copilot-swe-agent[bot] Claude: 147,000 https://github.com/search?q=is%3Apr+in%3Abody+%28%22Generate... - is:pr in:body ("Gener…

That's a denominator of total. How many are actually useful?

Re: LLMs are the ultimate demoware

#57

Post by turnsout »

lomase wrote: post #53
turnsout wrote: post #8

This is such a weak take to read while I have Claude Code running in the background creating a new database migration for a feature we're building

Can't your stack do that for you? The one I use creates the migrations, locally, for free and deterministically in about 30 seconds.

I'm using raw Postgres. I don't like a lot of dependencies or "stacks" where they don't need to be. Claude does this extremely efficiently.

Re: LLMs are the ultimate demoware

#58

Post by AnotherGoodName »

pjc50 wrote: post #34
tptacek wrote: post #7

It's wild to me that, of all the things to call LLMs out for, this piece has chosen to include math tutoring. I've been doing Math Academy for a bit over 6 months now, going from (essentially) Algebra II through Calc II (integration by parts, arc lengths, Taylor expansions) and LLMs have been a huge part of what has made that effective: * Clear explanation of concepts that respond to questions and reformulate when th…

Is it always correct?

I've used LLMs to try to help digest some advanced maths. Eg. "Explain the number field seive with lots of numeric examples".

Yes the numeric examples often don't work. The consequences of this though are similar to a failed web search. As in it's not a big deal and when it does work it's very helpful.

Maths is one of those things with so much objectivity that even the LLM usually realizes it has failed to create a numeric example. "Here the numeric example breaks down since we cannot find a congruence of squares in this example without finding more B-smooth numbers in step 1". Ok that's a shame, i would have loved to see an end to end numeric example.

I think people get too hung up on any possibility of LLMs not being perfect while still being extremely helpful.

Re: LLMs are the ultimate demoware

#59

Post by getnormality »

simonw wrote: post #50
getnormality wrote: post #45

Earlier quoted context omitted.

I think before that question is useful to ask, we have to know if that FAQ even says anything about LLM-based tutoring. After a few minutes of research, I can't find any evidence that Math Academy offers LLM-based tutoring.

This was linked from the homepage: https://www.mathacademy.com/how-our-ai-works But more importantly if tptacek says they use LLMs and is a user of the platform that's good enough for me.

Everything described there sounds like old-school adaptive algorithms. I don't see anything about generative AI or LLMs.

I asked Google if MA does LLM tutoring and got back this answer:

> Math Academy does not offer Large Language Model (LLM) tutoring. While the company advertises itself as "AI-powered," this is in reference to a machine-learning-based adaptive learning system, not an interactive LLM tutor.

And here is a HN comment that indicates LLMs are a complement to MA, not part of it: https://news.ycombinator.com/item?id=43281240

Re: LLMs are the ultimate demoware

#60

Post by csmeyer »

tptacek wrote: post #13
empath75 wrote: post #10

Earlier quoted context omitted.

It seems very hard to maintain the belief that LLMs are useless in the face of the fact that millions of people are using them. It's very much "nobody goes there anymore, it's too crowded"

I think you'd be crazy to say LLMs are blockchain-style hype when it comes to software development but I don't begrudge anybody who believes they're not currently workable for the kinds of problems they work on; I think reasonable people can disagree about how ready for prime time they are for production software development. But for math tutoring? If you claim LLM math tutoring is demoware, you're very clearly telli…

(OP) In my post, I actually ask the question of whether a student would _want_ to interact with the tutor, not if the tutor is capable of providing good instruction. These are drastically different critiques.
Post reply on HN