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

I trusted an LLM, now I'm on day 4 of an afternoon project

nemo.foo

Post reply on HN
Print view View original

161–170 of 215 posts

Re: I trusted an LLM, now I'm on day 4 of an afternoon project

#161

Post by satvikpendem »

BalinKing wrote: post #126
maybesomaybenot wrote: post #82

Earlier quoted context omitted.

Claude is like having my own college professor. I've learned more in the past month with Claude then I learned in the past year. I can ask questions repeatedly and get clarification as fine as a need it. Granted, Claude has limits, but its a game-changer. > I think the key to being successful here is to realize that you're still at the wheel as an engineer. The llm is there to rapidly synthesize the universe of infor…

> Claude is like having my own college professor. I don't use Claude, so maybe there's a huge gap in reliability between it and ChatGPT 4o. But with that disclaimer out of the way, I'm always fairly confused when people report experiences like these—IME, LLMs fall over miserably at even very simple pure math questions. Grammatical breakdowns of sentences (for a major language like Japanese) are also very hit-or-miss.…

> LLMs fall over miserably at even very simple pure math questions

They are language models, not calculators or logic languages like Prolog or proof languages like Coq. If you go in with that understanding, it makes a lot more sense as to their capabilities. I would understand the parent poster to mean that they are able to ask and rapidly synthesize information from what the LLM tells them, as a first start rather than necessarily being 100% correct on everything.

Re: I trusted an LLM, now I'm on day 4 of an afternoon project

#162

Post by satvikpendem »

Eisenstein wrote: post #119
malfist wrote: post #110

Earlier quoted context omitted.

My college professor has certifications and has passed tests that weren't in their training data. My college professor was also willing to say "I don't know, ask me next class"

What do you consider 'not in its training data'? I just asked Claude a question I am pretty sure was not in its training data. * https://i.imgur.com/XjvImeT.jpeg

Did you actually test the math done? Usually LLMs are terrible at math as, as I mentioned in another comment, they are language models, not calculators. Hopefully that changes when LLMs leverage other apps like calculators to get their results, I am not sure if Claude does that already or it's still in development.

Re: I trusted an LLM, now I'm on day 4 of an afternoon project

#163

Post by satvikpendem »

baxtr wrote: post #33
potsandpans wrote: post #10

Counterexample: Ive been able to complete more side projects in the last month leveraging llms than i have ever in my life. One of which I believe to have potential as a viable product, and another which involved complicated rust `no_std` and linker setup for compiling rust code onto bare metal RISCV from scratch. I think the key to being successful here is to realize that you're still at the wheel as an engineer. Th…

Is it reasonable to assume that more senior devs benefit more from LLMs?

It's the LLM paradox, seniors get more senior with them while juniors get more junior, creating a bimodal distribution in the future simply because juniors will start depending on them too much to learn how to code properly while seniors (who some may also exhibit the previous trait) will by and large be able to rapidly synthesize information from LLMs with their own understanding.

Re: I trusted an LLM, now I'm on day 4 of an afternoon project

#164

Post by NitpickLawyer »

suddenlybananas wrote: post #55
NitpickLawyer wrote: post #32

Earlier quoted context omitted.

> vs most things related to hardware or low level work. counter point: https://github.com/ggerganov/llama.cpp/pull/11453 > This PR provides a big jump in speed for WASM by leveraging SIMD instructions for qX_K_q8_K and qX_0_q8_0 dot product functions. > Surprisingly, 99% of the code in this PR is written by DeekSeek-R1. The only thing I do is to develop tests and write prompts (with some trials and errors)

at a certain point though, one wonders if you can trust people to accurately report how much is written by an LLM. (not even implying bad faith, but if you're constantly re-reading, selecting and re-combining snippets written by LLMs, it's not really "written" by LLMs in the same way that's implied).

> at a certain point though, one wonders if you can trust people to accurately report how much is written by an LLM.

That's an interesting thought. I think there are ways to automate this, and some IDEs / tools track this already. I've seen posts by both Google and Amz providing percentages of "accepted" completions in their codebases, and that's probably something they track across codebases automatically.

Also on topic, here's aider's "self written code" statistics: https://aider.chat/HISTORY.html

But yeah I agree that "written by" doesn't necessarily imply "autonomously", and for the moment it's likely heavily curated by a human. And that's still ok, IMO.

Re: I trusted an LLM, now I'm on day 4 of an afternoon project

#165

Post by satvikpendem »

mordymoop wrote: post #41

I am frankly tired of seeing this kind of post on HN. I feel like the population of programmers is bifurcating into those who are committed to mastering these tools, learning to work around their limitations and working to leverage their strengths… and those who are committed to complaining about how they aren’t already perfect Culture Ship Minds. We get it. They’re not superintelligent at everything yet. They couldn…

Use uBlock Origin to block posts with the keywords you don't want in the title, like AI or LLM.

Re: I trusted an LLM, now I'm on day 4 of an afternoon project

#167

Post by Eisenstein »

satvikpendem wrote: post #162
Eisenstein wrote: post #119

Earlier quoted context omitted.

What do you consider 'not in its training data'? I just asked Claude a question I am pretty sure was not in its training data. * https://i.imgur.com/XjvImeT.jpeg

Did you actually test the math done? Usually LLMs are terrible at math as, as I mentioned in another comment, they are language models, not calculators. Hopefully that changes when LLMs leverage other apps like calculators to get their results, I am not sure if Claude does that already or it's still in development.

Claude has access to an analysis frame which takes javascript which it can use for calculations.

Re: I trusted an LLM, now I'm on day 4 of an afternoon project

#168

Post by Eisenstein »

selcuka wrote: post #141
Eisenstein wrote: post #119

Earlier quoted context omitted.

What do you consider 'not in its training data'? I just asked Claude a question I am pretty sure was not in its training data. * https://i.imgur.com/XjvImeT.jpeg

That's almost in the training data: https://www.quora.com/How-many-Humans-can-we-fit-on-the-Moon

I guess coming up with a truly original question is tougher that it seems. Any ideas?

Re: I trusted an LLM, now I'm on day 4 of an afternoon project

#169

Post by maybesomaybenot »

malfist wrote: post #110
selcuka wrote: post #108

Earlier quoted context omitted.

They are reasonably accurate, and no tutor is perfect. How do you know your college professor is accurate?

My college professor has certifications and has passed tests that weren't in their training data. My college professor was also willing to say "I don't know, ask me next class"

You can also test your professor's answers. I don't just walk around going "Oh, Claude was right", I'm literally using what I just learned and am generating correct results. I'm not learning facts like dates, or subject things, I'm learning laws, equations, theories, proofs, etc. (Like how to apply Euler's totient or his extended theories on factorization... there's only one "right answer").

Also, you method for attesting your professors accuracy is inherently flawed. That little piece of paper on their wall doesn't correlate with how accurate they are; it doesn't mean zero, but it isn't foolproof. Hate to break it to you, but even heroes are fallible.

Re: I trusted an LLM, now I'm on day 4 of an afternoon project

#170

Post by pinoy420 »

potsandpans wrote: post #10

Counterexample: Ive been able to complete more side projects in the last month leveraging llms than i have ever in my life. One of which I believe to have potential as a viable product, and another which involved complicated rust `no_std` and linker setup for compiling rust code onto bare metal RISCV from scratch. I think the key to being successful here is to realize that you're still at the wheel as an engineer. Th…

Exactly this. OP, credit where credit is due, appears to be someone who “hacks things together” copy pasting solutions blindly from the internet - with little intuition gained along the way.
Post reply on HN