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

Let's talk about LLMs

b-list.org

Post reply on HN
Print view View original

41–50 of 201 posts

Re: Let's talk about LLMs

#41

Post by aspenmartin »

slopinthebag wrote: post #32
atleastoptimal wrote: post #16

"LLM's Aren't Going to Fundamentally Change Software Development" Says Increasingly Nervous Man For Seventh Time This Year

I didn't get the sense that the author is nervous. What I tend to see are people who are nervous that going all-in on LLM workflows might not have the payoff they are expecting, and are becoming increasingly fanatical as a result. Just one more harness bro. Just one more agentic swarm. Please bro, just one more Claude Max subscription. Please bro.

You say this as though performance has not followed a very clear and extremely rapid improvement in a startlingly short amount of time.

You’re definitely right that people adopt agentic workflows and are disappointed or worse, but the point is the disappointment has already reduced substantially and will continue to do so. We know this because we know the scaling laws, and also because learning theory has been around for many decades.

Re: Let's talk about LLMs

#42

Post by stackghost »

jubilanti wrote: post #30
stackghost wrote: post #3

Let's actually not talk about LLMs. I honestly couldn't force myself to finish yet another blog post about how "we're not yet sure what impact LLMs will have on society" or whatever beleaguered point the author was attempting to make. "Some random person's take on LLMs" was maybe interesting in 2024. Today it is not even remotely interesting. There are a gazillion more interesting things happening today that ought to…

I'm confused. If you don't want to talk about LLMs then why didn't you just flag the post and move on? Submit something interesting, upvote and comment on interesting posts, instead of feeding the engagement on this thread. It sounds like you actually do want to talk about how much you don't want other people to talk about LLMs.

Oh, I definitely flagged the post also.

Re: Let's talk about LLMs

#43

Post by imiric »

mfro wrote: post #4

I think you're misunderstanding the paradigm shift completely -- AI does not just generate code N(x) more quickly. It thinks N(x) faster, it researches N(x) faster, it tests N(x) faster. There are hundreds of tasks that you'll find engineers are offloading to AI every day. The major hurdle right now is actually pivoting LLMs from just generating code: integrating those tasks into workflows. This is why tool-use and a…

> The major hurdle right now is actually pivoting LLMs from just generating code: integrating those tasks into workflows.

Funny, I thought that the major hurdle is improving accuracy and reliability, as it's always been. Engineering is necessary and useful, but it's a much simpler problem, which is why everyone is jumping on it.

Re: Let's talk about LLMs

#44

Post by radarsat1 »

michaelchisari wrote: post #38
jb1991 wrote: post #37

Earlier quoted context omitted.

Funny, I have the complete opposite impression after using claude code for a while. I would never trust it to design anything. Never again. But it can code pretty well given a very tight and limited scope.

To clarify, AI should not do the design itself. You develop the design in conversation with AI. I come in knowing what I need to build and at least one idea or more of how it should be done. I present the problem, constraints, potential solutions, and ask for criticisms and alternatives. I can keep it as broad as possible or I can get more granular like struct layouts, api endpoints, etc. I go back and forth until th…

> It's wildly better at tight and limited scope than large scale changes but even then I would rather code it myself.

One thing I would like to see is the use of LLMs for smarter semi-manual editing.

While programming I often need to make very similar changes in several places. If the instances are similar enough I can get away with recording a one-off keyboard macro to repeat, but if there are differences that are too difficult to handle this way I end up needing to do a lot of manual editing.

It would be nice to see LLMs tightly integrated into the editor so I can do a simple "place the cursor at things like this" based on an example or two. I'm sure more ideas for using LLMs more quickly perform semantic changes you intended are possible, instead of just prompting for a big diff. I feel there's a lot more innovation possible in this direction, where you're still "coding it yourself" but just faster.

Re: Let's talk about LLMs

#45

Post by paulhebert »

CamperBob2 wrote: post #39
frizlab wrote: post #21

Earlier quoted context omitted.

> There is no reason to believe that future AI platforms won't be able to review code themselves and manage some aspects of themselves with minimal human oversight There are, IMHO, fewer reasons to believe they will be able to do that rather than not, though.

LLMs became much better at both reviewing and writing code over the last 12-18 months. Did you? The current state of the art is irrelevant. Only the first couple of time derivatives matter.

> Did you?

I would say I got better at both of those over the last 12-18 months. Are your skills static?

Re: Let's talk about LLMs

#46

Post by tptacek »

oytis wrote: post #34
mfro wrote: post #4

I think you're misunderstanding the paradigm shift completely -- AI does not just generate code N(x) more quickly. It thinks N(x) faster, it researches N(x) faster, it tests N(x) faster. There are hundreds of tasks that you'll find engineers are offloading to AI every day. The major hurdle right now is actually pivoting LLMs from just generating code: integrating those tasks into workflows. This is why tool-use and a…

The article addresses exactly this objection. Most importantly, it quotes that AI coding tools have a detrimental effect on software stability - which is basically raison d'etre for our profession. When it produces more robust software and handles on-call shifts better than humans, I will consider programming done.

I'm excited to read the first cogent piece making this point that doesn't devolve to gatekeeping, a detached and vaguely hostile professional software developer telling people with a newfound capability to solve practical problems for themselves with new software that they don't or shouldn't want the thing that they want, because whatever it is they come up with won't be "fit for purpose" until blessed by the guild, which has bylaws extrapolated from Brooks about the fundamental "limitations of LLMs".

Re: Let's talk about LLMs

#48

Post by oytis »

tptacek wrote: post #46
oytis wrote: post #34

Earlier quoted context omitted.

The article addresses exactly this objection. Most importantly, it quotes that AI coding tools have a detrimental effect on software stability - which is basically raison d'etre for our profession. When it produces more robust software and handles on-call shifts better than humans, I will consider programming done.

I'm excited to read the first cogent piece making this point that doesn't devolve to gatekeeping, a detached and vaguely hostile professional software developer telling people with a newfound capability to solve practical problems for themselves with new software that they don't or shouldn't want the thing that they want, because whatever it is they come up with won't be "fit for purpose" until blessed by the guild,…

I am less sure about his argument about democratising software indeed. The only problem in my own life that I solve with software is a problem of getting paid, so what do I know. If someone can generate a piece of code for their needs, and they don't risk harming anyone but themselves, then it's a great application of LLMs.

Re: Let's talk about LLMs

#49

Post by slopinthebag »

aspenmartin wrote: post #41
slopinthebag wrote: post #32

Earlier quoted context omitted.

I didn't get the sense that the author is nervous. What I tend to see are people who are nervous that going all-in on LLM workflows might not have the payoff they are expecting, and are becoming increasingly fanatical as a result. Just one more harness bro. Just one more agentic swarm. Please bro, just one more Claude Max subscription. Please bro.

You say this as though performance has not followed a very clear and extremely rapid improvement in a startlingly short amount of time. You’re definitely right that people adopt agentic workflows and are disappointed or worse, but the point is the disappointment has already reduced substantially and will continue to do so. We know this because we know the scaling laws, and also because learning theory has been around…

Yes but we don't know the shape of the curve and where we are on it.

Re: Let's talk about LLMs

#50

Post by paganel »

mfro wrote: post #4

I think you're misunderstanding the paradigm shift completely -- AI does not just generate code N(x) more quickly. It thinks N(x) faster, it researches N(x) faster, it tests N(x) faster. There are hundreds of tasks that you'll find engineers are offloading to AI every day. The major hurdle right now is actually pivoting LLMs from just generating code: integrating those tasks into workflows. This is why tool-use and a…

> , it tests N(x) faster.

It does? You mean "it tests itself faster", which is not really a test now, is it?

Post reply on HN