> Don't use it to write code. It's a terrible programmer.

I see this sentiment often, and I’m honestly not sure where this comes from, as it’s really not been my experience. I feel like this must come from people feeling threatened and just moving the goals posts, or not knowing how to use the tools effectively.

> I see this sentiment often, and I’m honestly not sure where this comes from, as it’s really not been my experience

If you see people saying it often, but you are convinced they are just feeling threatened, what AI generated software would point to to say, "Look at this! Definitive evidence that they are just coping!"

Well, for one thing, I’d point to all the other anecdotes of developers being made 10x more efficient due to LLM use.

But really I’m just comparing against my personal experience. Once I learned how to use the tools well, and what to expect (and what not to), I’ve found LLMs to be very powerful.

>If you see people saying it often, but you are convinced they are just feeling threatened, what AI generated software would point to to say, "Look at this! Definitive evidence that they are just coping!"

This is a trap. Anyone who answers this will see the goalposts being moved yet again.

95% of our code at a top in market global fintech is now written by agents. We make it write good code, and it does.

This is very vague. Maybe you could actually name the fintech (or, if that is too sensitive), you can list a few of its competitors?

GitHub

/s

I see your sentiment quite often here on HN¹, I'm honestly not sure what kind of experience you may have had with automatic program writers. LLM code absolutely sucks.

1 - I wonder why my other social circles are so different.

I am really curious about this because my experience is completely different. Can you elaborate a bit more on how you use LLM's for coding? Are you doing one-shot coding? Vibe coding (not looking at code)? Small focused one-step-at-a-time with yourself verifying? Anything else?

It's a common enough experience that it shouldn't be dismissed.

I think language, frameworks, domain and style can all influence the quality of the output. I think it’s hard to compare experiences.

I think a lot of the people saying AI code sucks is because the code isn't formatted the way they like, not because the code doesn't work.

Basically, the people that leave dozens of bikeshed code review comments.

Sure, sometimes I might ask the AI to break out a helper function or structure things differently, but that's the same as working with another dev

I've witnessed SQL executed with a where clause be wrapped in a function which then iterates over the result to re-enforce the where clause.

People need to read the slop they're throwing at reviewers.

It's a mistake to let AI write code unsupervised by a human. I tend to let it write code and then iterate on it. Sometimes myself (because explaining would take longer than actually doing it) sometimes I prompt the AI to improve specific points.

Have you seen how poor the Claude Code codename is?

If that's what the token providers themselves can get out of their SOTA models, imagine how bad it is for other companies.

I agree. Claude Code (for example) writes excellent code as long as the prompt is focused and clear.

Regarding 2

Isn't it possible that people who think LLMs are awesome at coding are in fact bad at it themselves, leading to them over estimating the LLMs "skill"?

To me it feels like people telling on themselves that they aren't very good

30+ years of experience here writing everything from JIT high-performance compilers to professional game engines to mission critical biz servers:

Claude Code is excellent at writing (C++) code. Especially multi-threading code. However I still need to verify everything because it will occasionally make mistakes.

Guess I'm the one who is delusional then

Oh well. Time to start building a new career before I'm completely irrelevant I guess

I don’t consider myself an expert, but I’ve been programming for the last 6 years, and of those 6 years I’ve spent almost all my spare time programming during this period except for a 1 year hiatus.

This includes personal projects with a decent amount of users, and 1 sold project. I’m not the best programmer, but I wouldn’t say I’m bad at all.

Question to you, have you actually used a leading model like Fable when it was available? I did. I was seriously impressed.

I’ll be honest I find it hard to take anyone seriously who says they can program better or faster than a model with those capabilities. That has not been my experience.

Architecting - yes people are still better overall. LLMs tend to go with the average middle of the road result. But in terms of output, raw speed, and getting something working? No way am I better than an llm.

Happy to be enlightened and told I’m completely wrong. Maybe I am an idiot. That is a possibility.

But how about I give you a task, and I give Claude that same task, and we compare results against execution speed? I’ll happily be the judge of that.

People are generally bad at judging themselves, and for some reason even worse about judging their agents' output.

I've heard a million people say their LLM workflow produces amazing code. But I have never actually seen the amazing code allegedly being produced. Where are the people saying "I love when my coworkers send me AI-generate PRs"?

“Amazing code”… who cares?

that’s like saying a book is only worth reading if each sentence is beautiful

To me I couldn’t care less as long as the overall story is coherent, and I care more about the idea density in the book.

Lord of the rings is a great book because of the ideas, not because Tolkien is the best writer ever.

Same with AI. I couldn’t care less if some of its code is crap, if it is dense with ideas and generally good execution. If it writes crap code sections I can “beautify” myself.

Plus LLMs are only going to improve… they have improved so much since ChatGPT 3. It’s insane.

And the arguments saying they haven’t can’t be taken in good faith

I mean sure. It can get stuff done faster

So can just copying from Stack Overflow, or taking from Open Source repos

There have always been reasons why we didn't prefer to do that in the past, but I guess laundering it through LLMs is fine. And that's just the tip of the ethical ice berg

High volumes of unvetted code is a bad practice. If the code winds up working out fine then congrats you won the slot machine. It's still a bad practice and very, very stupid to become reliant on

And by the way, I had been programming for longer than you have before I even graduated high school, if that matters

But we aren’t discussing ethics here, we are discussing technical capabilities.

Who said it’s unvetted?

Sure it matters

Was it repressed? It doesn’t look to be significantly less prevalent than other 9s from the histogram.

He sold his business. That tends to happen quite a bit.

Yeah, historically it’s been software that’s limited AMD here. Not surprised to hear that may still be the issue. NVidia’s biggest edge was really CUDA.

CUDA is a complete and utter piece of shit software. It's just that it is a tiny bit less of a shitshow than the alternatives.

It’s not that they don’t have it. It’s that they don’t want it.

Software aside, does AMD have a potential strategic advantage in the long term since they are also producing top tier CPUs? Is there some future benefit to tightly integrating their products? IIRC NVidia partnered with intel for this purpose, right?

I’ve been wondering about this. It used to be that different chip makers had different efficiencies, and so measuring two different companies chips in gigawatts wouldn’t be a good apples to apples comparison.

Is that still true or has the gap narrowed? Or have GPUs always been similar across the board and it’s CPUs that have more disparity?

Franklin Templeton | Quant Implementation Lead | Boston, MA | In-Person | $145k - $190k + Bonus

We're building an end-to-end portfolio construction system to support FTIS, a $100bn multi-asset investment manager within FT. This is a front office role that will help guide our quantitative staff as we build out this new system. This project is a strategic objective for FTIS, highly visible, and frankly one of the most fun jobs in the industry.

We're looking for mid to senior level researchers or developers with strong buy-side backgrounds who can help translate our investment process into a robust, scalable, and approachable design.

Reach out with any questions - dan.nadler (at) franklintempleton (dot) com

Apply here: https://franklintempleton.wd5.myworkdayjobs.com/Primary-Exte...

I think maybe this refers to unlearning wrong information?

Also abstracting. No need to remember every milliseconds in its lifetime and consult them in every query.

I can remember for example when I was wrong and how and still responding correctly, I don't have to forget my wrong answer to respond with the correct one.

I have a similar mindset though less focused on the type of questions being asked and more about how many times I have to answer the same question.

Ideally, the number is one time. As in one conversation where the person walks away understanding the answer. If I have to have that conversation more than once it’s a problem.

Obviously there’s nuance - it can take time to get your head around a new concept or hard problem. But in any case, I like that as one dimension when thinking about a person’s skill/level/potential.

> I have a similar mindset though less focused on the type of questions being asked and more about how many times I have to answer the same question.

Yes, I completely agree and do that as well.

The focus on “type of question” has been something I’ve done more recently after helping someone out. Just reflecting on “what type of problem did I just help solve and how can I make it easier for them to solve on their own in the future”. Very often the answer is “more documentation” or similar, getting things only in my head down where everyone can benefit. On the other hand I walk away from some problems I’ve helped with frustrated that the answer was 1-2 Google searches away and the issue had nothing to do with “our stack”.

I mostly agree with you, but there’s another angle that is similar. How many times does the person come to you with a similar question but on a slightly different topic and you need to guide them through _how to find_ the answer. I’ve supervised mid level engineers in the past who will just drop a stack trace in a slack DM and expect me to tell them what’s wrong - I didn’t write the code so why do you expect me to figure it out for you. But when I have the conversation of “we’ve talked about how to dxooore these kinds of problems a few times now, next time you need to apply these techniques”,it often doesn’t land.