161–170 of 527 posts
The o1 model is really remarkable. I was able to get very significant speedups to my already highly optimized Rust code in my fast vector similarity project, all verified with careful benchmarking and validation of correctness. Not only that, it also helped me reimagine and conceptualize a new measure of statistical dependency based on Jensen-Shannon divergence that works very well. And it came up with a super fast i…
> 1,337 additions cough
Earlier quoted context omitted.
That’s fine until your code makes its way to production, an unconsidered side effect occurs and then you have to face me. You are still responsible for what you do regardless of the means you used to do it. And a lot of people use this not because it’s more productive but because it requires less effort and less thought because those are the hard bits. I’m collecting stats at the moment but the general trend in quali…
Ugh, dude, I used to push bad code into production without ChatGPT. It is such a stupid argument. Do you really think people are just blindly pushing code they can't make heads or tails of? That they haven't tested? Do you seriously think people are just one shotting code and blasting it into prod? I am completely baffled by people in this industry that just don't get it . Learn to prompt. Write tests. Wtf.
I literally had someone with the balls to tell me that it was ChatGPT's fault.
Due diligence and intelligence has shit the fucking bed quite frankly.
Earlier quoted context omitted.
That’s fine until your code makes its way to production, an unconsidered side effect occurs and then you have to face me. You are still responsible for what you do regardless of the means you used to do it. And a lot of people use this not because it’s more productive but because it requires less effort and less thought because those are the hard bits. I’m collecting stats at the moment but the general trend in quali…
Ugh, dude, I used to push bad code into production without ChatGPT. It is such a stupid argument. Do you really think people are just blindly pushing code they can't make heads or tails of? That they haven't tested? Do you seriously think people are just one shotting code and blasting it into prod? I am completely baffled by people in this industry that just don't get it . Learn to prompt. Write tests. Wtf.
Yes, and I see proof of it _literally every day_ in Code Reviews where I ask juniors to describe or justify their choices and they shrug and say "That's what Copilot told me to put".
Tao mentions grad students; I wonder how they feel reading this? As LLMs continue to improve I feel like anyone making a living doing the "99% perspiration" part of intellectual labor is about to enter a world of hurt.
> The experience seemed roughly on par with trying to advise a mediocre, but not completely incompetent, graduate student. And you thought you had imposter syndrome before!
Earlier quoted context omitted.
> I've found that I haven't written a line of code in weeks Which is great until your next job interview. Really, it's tempting in the short run but I made a conscious decision to do certain tasks manually only so that I don't lose my basic skills.
This. I’ve been using elixir for ~6 months (guided by Claude) and probably couldn’t solve fizz buzz at a whiteboard without making a syntax error. Eek.
Earlier quoted context omitted.
> But no one really show how they're actually solving problems with LLMs and how the alternatives were worse for them. It's all claims that it's great with no further elaboration on the workflows. To give an example, one person (a researcher at DeepMind) recently wrote about specific instances of his uses of LLMs, with anecdotes about alternatives to each example. [1] People on HN had different responses with similar…
> (often misquoted) phrase You misquoted it there! It should be: The plural of anecdote is data.
There’s at least a “complexity” if not a “problem” in terms of judging models that to a first approximation have been trained on “everything”.
Have people tried putting these things up against serious mathematical problems that are well studied? With or with Lean hinting has anyone gotten like, the Shimura-Taniyama conjecture/proof out?
Earlier quoted context omitted.
I entirely agree about their utility. HN, and the internet in general, have become just an ocean of reactionary sandbagging and blather about how "useless" LLMs are. Meanwhile, in the real world, I've found that I haven't written a line of code in weeks. Just paragraphs of text that specify what I want and then guidance through and around pitfalls in a simple iterative loop of useful working code. It's entirely a lea…
What sort of problems do you solve? I tried to use it. I really did. I've been working on a tree edit distance implementation base on a paper from 95. Not novel stuff. I just can't get it to output anything coherent. The code rarely runs, it's written in absolutely terrible style, it doesn't follow any good practices for performant code. I've struggled with getting it to even implement the algorithm correctly, even t…
Try starting from ground zero and guiding it to the solution rather than trying to one shot your entire solution in one go.
I want you to implement this kind of tree in language x.
Ok good, now I want you to modify it to do Y.
Etc.