Hacker Newsnew | past | comments | ask | show | jobs | submit | almoehi's commentslogin

What I found in practise is that AI generated code is typically 30% longer than it should be compared to how an experienced senior would write it.

It’s not that it is wrong or anything - it’s just unnecessary verbose.

Which you could argue is not a problem if it won’t be read by humans anyways anymore in the near future.


> Which you could argue is not a problem if it won’t be read by humans anyways anymore in the near future.

It's a problem right now for code that isn't being read by humans.

LLM-backed agents start by writing slightly bad code that's a little too verbose, too careful in error handling, writes too much fallback code, among other common minor LLM-ish flaws. And then it's next turn of the crank sees all that, both as an example but also as code it must maintain, and is slightly more bad in all those ways.

This is why vibing ends up so bad. It keeps producing code that does what you asked for a fairly long time, so you can get a long way vibing. By the time you hit a brick wall it will have been writing very bad code for a long while, and it's not clear that it's easier to fix it than start over and try not to accept any amount of slop.


> too careful in error handling, writes too much fallback code

Is it possible that your code goes a little cowboy when it comes to error handling? I don't think I've ever seen code that was too careful when it came to error handling -- but I wrote GPU drivers, so perhaps the expectations were different in that context.


I’ve definitely seen agents add null checks to a computed value in a function, but then not change the return type to be non-null. Later, it adds a null checks at each call site, each with a different error message and/or behavior, but all unreachable.

For bonus points, it implements a redundant version of the same API, and that version can return null, so now the dozen redundant checks are sorta unreachable.


When I'm writing web services I think I handle almost every error and I don't have this complaint there.

When I'm writing video games there's lots of code where missing assets or components simply mean the game is misconfigured and won't work and I would like it to loudly and immediately fail. I often like just crashing there. There are better options sometimes too, making a lot of noise but allowing continuation. But LLMs seem to be bad at using those too.

Actually to go back to web services, I do still hate the way I've had LLMs handle errors there too - too often they handle them silently or worse, provide some fallback behavior that masks the error. They just don't write code that looks like it was written by someone with 1) some assumptions about how the code is going to be used 2) some ideas about how likely their assumptions are to be wrong or 3) some opinions about how they'd like to learn their assumptions are wrong if so.


I’ve had written up a proposal for a research grant to basically work exactly on this idea.

It got reviewed by 2 ML scientists and one neuroscientist.

Got totally slammed (and thus rejected) by the ML scientists due to „lack of practical application“ and highly endorsed by the neuroscientist.

There’s so much unused potential in interdisciplinary research but nobody wants to fund it because it doesn’t „fit“ into one of the boxes.


Make sure the ML scientists don't take credit for your work. Sometimes they reject a paper so they can work on it on their own.


Grant reviews are blind reviews - so you don’t know. Also - and even worse - there is no rebuttal process. It gets rejected without you having a chance to clarify / convince reviewers.

Instead you’d need to resubmit and start the entire process from scratch. What a waste of resources …

It’s the final nail what made me quit pursuing a scientific career path despite having good pubs & PhD /w honours.

Unfortunately it’s what I enjoy the most.


That's unfortunate. My personal sense is that while agentic LLM's are not going to get us close to AGI, a few relatively modest architectural changes to the underlying models might actually do that, and I do think mimicry of our own self-referential attention is a very important component of that.

While the current AI boom is a bubble, I actually think that AGI nut could get cracked quietly by a company with even modest resources if they get lucky on the right fundamental architectural changes.


I agree - and I think having interdisciplinary approach here is going to increase the odds here. There is a ton of useful knowledge in related disciplines - often just named differently - but turns out investigating the same problem from a different angle.


Sounds like those ML "scientists" were actually just engineers.


A lot of progress is made through engineering challenges

This is also "science"


Procurify | Fully Remote, CANADA | FULL-TIME | REMOTE | 150k-230k CAD

- Director Data Engineering & Data Science (https://boards.greenhouse.io/procurify/jobs/4352825005)

(80% hands on at the beginning)

- Senior Data Engineer (https://boards.greenhouse.io/procurify/jobs/4352787005)

We’re assembling a small but mighty team to build and own the data platform that’s going to be the backbone of the business' strategic shift towards automation and data-driven products in the procure-to-pay industry. You’ll get the opportunity to work on the largest technology initiative since the company's founding about 10y ago. An opportunity with massive impact, visibility and full buy-in from the senior leadership and executives.

Our mission is to enable our gang of 40+ product engineers to deliver data-driven products and features.

Profile (roughly):

- great personality

- solid engineering skills with Python and pyspark / deltalake

- data architecture and data modelling

- CI/CD, testing and quality tests for data pipelines

- experience with databricks and its recent products highly desired (deltalake, autoloader, unity catalog, structured streaming, DLT, DAB, ...)

Some highlights:

- 4-day work week (every Friday off)

- Well funded as we just raised 50m in series C

- Excellent senior leadership with a human-centric culture

- Great business momentum and growth trajectory

Put "hackernews" into the last textbox and I'll make sure it gets in front of our recruiter and hiring manager.


Hi, you have your links backward. The Director role links to the Data Eng role, and vice versa.


Sounds like LLMs having their SQL injection equivalent moment.

I’d also say this described phenomenon isn’t new - except for it’s applied context: it’s essentially disinformation - a well known technique used by military since decades. Except now we hack LLM agents instead of real people’s minds.

Nonetheless interesting to watch.


Yup, I think this is analogous to a "Second Order SQL Injection"


Nice and slim - does your cubic spline support clamping and monotonicity as well by any chance ?


Do you have an example or reference describing how clamping and monotonicity in the context of cubic splines are implemented? Thanks.


https://en.wikipedia.org/wiki/Monotone_cubic_interpolation has some reference for monotone cubic splines.

In theory they should be useful when know that the underlying process should be monotone. I think in the past I found them more sensitive to noise and wondered if monotone approximation might not be better than monotone interpolation for that reason.


I added class comments to each class which explain the high level implementation details. Clamping is supported with natural cubic splines, and this is done by taking the slopes at each endpoint.

Monotonicity is currently not supported (for cubic splines).


The general assumption you make is wrong - it’s not like in North americas. There are eng jobs in the top bracket, but the big majority isn’t.


Your website has no content as of now, so would you mind sharing one sentence what you’re doing/building - at least roughly? SaaS, product, ML ... ?


Sending out responses to applications would actually be nice ... just saying.


I know it's frustrating not to get a response, but this comment breaks the rules at the top of the thread. Please don't do that here.


Well, I’m not complaining, I’m suggesting an automated reply to notify people that their stuff was submitted. Which is how things usually work when you submit through a recruiting portal.

I’m not complaining about the processing “speed”.


That wasn't clear in your comment. I read it more as a snarky way of complaining that you applied and didn't hear back.

I agree with you that job applicants should get responses.


I heard similar things, but it also seems to be very specific to Zurich area. Maybe due to the high ratio of expats per locals.


FYI: your https website is not loading. Plus, neither your post nor the non-https version of your website provides any information on what you're actually looking/recruiting for. Probably not the best way to attract people.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: