People will downvote you because this comment is "not appropriate" for HN, but there were countless conversations on HN about how important these benchmarks are. I am literally LOLing at HN right now
> AI is also scarily good at writing tests :-) I hope you read those tests before claiming it's "scary good"
This is such a bad take. I'm impressed how often this gets parroted online. Next time, please check how many Poles left Poland for western EU since they joined.
yeah. In the future when? 2, 3, 5 years from now on? Do you think current LLMs don't get confused by shitty code? That code they're writing now will need fixing tomorrow, not 5 years later.
I have the same feeling ever since his infamous LLM OS post
> I'll make more progress than mentally wearing myself out reading a bunch of LLM generated code trying to figure out how to solve the problem manually. Most engineers realize that there's currently more tech debt being…
> I'll make more progress than mentally wearing myself out reading a bunch of LLM generated code trying to figure out how to solve the problem manually. I feel sorry for whoever has to work on that codebase. This is the…
Totally agreed, this has been and will continue to be a problem for all existing models. > Like are programmers and engineers using LLMs completely differently than I'm doing No, but the complexity of the problem…
> what's needed is knowledge of solution techniques That's definitely in the training data
Ah right! Reminds me of AGI by 2025 :D
> The idea that code is something sacred and only devs can somehow do it is dying, and I personally love it, as I am watching it enable so many of my friends and family who have no idea how to code. People on HN are…
Yeah, good luck trusting the output!
Yeah, that's indeed a hot take. I am curious what kind of code you write for a living to have an opinion like this.
> well it actually implemented a normalization pipeline and a tax computing engine which then did the taxes, but close enough You can't seriously believe laymen will try to implement their own tax calculators.
Are you one of those naive people that still take these coding benchmarks seriously?
If this happens to software development, this will happen to most mental jobs.
CRUD
Oh, like the LLM OS?
Sure. Reading a book is a much more difficult and ultimately, productive, task than writing a book.
Ok I will bite. Every single example you gave is in a hobby project territory. Relatively self-contained, maintainable by 3-4 devs max, within 1k-10k lines of code. I've been successfully using coding agents to create…
We squash, but still rebase. For us, this works quite well. As you said, rebasing needs to be done carefully... But the main history does look nice this way.
Yeah. It's pretty telling to look at profiles of people who replied to his tweet.
Well put. The standard practice is to hire a scientist and a developer, both with deep expertise, and have them work together. For a successful collaboration, it's obviously desirable for them to have some…
Personally, hard disagree. There were improvements, yes, but the last year felt particularly stagnant to me
Did you claim the same a year or two ago? Why or why not?
People will downvote you because this comment is "not appropriate" for HN, but there were countless conversations on HN about how important these benchmarks are. I am literally LOLing at HN right now
> AI is also scarily good at writing tests :-) I hope you read those tests before claiming it's "scary good"
This is such a bad take. I'm impressed how often this gets parroted online. Next time, please check how many Poles left Poland for western EU since they joined.
yeah. In the future when? 2, 3, 5 years from now on? Do you think current LLMs don't get confused by shitty code? That code they're writing now will need fixing tomorrow, not 5 years later.
I have the same feeling ever since his infamous LLM OS post
> I'll make more progress than mentally wearing myself out reading a bunch of LLM generated code trying to figure out how to solve the problem manually. Most engineers realize that there's currently more tech debt being…
> I'll make more progress than mentally wearing myself out reading a bunch of LLM generated code trying to figure out how to solve the problem manually. I feel sorry for whoever has to work on that codebase. This is the…
Totally agreed, this has been and will continue to be a problem for all existing models. > Like are programmers and engineers using LLMs completely differently than I'm doing No, but the complexity of the problem…
> what's needed is knowledge of solution techniques That's definitely in the training data
Ah right! Reminds me of AGI by 2025 :D
> The idea that code is something sacred and only devs can somehow do it is dying, and I personally love it, as I am watching it enable so many of my friends and family who have no idea how to code. People on HN are…
Yeah, good luck trusting the output!
Yeah, that's indeed a hot take. I am curious what kind of code you write for a living to have an opinion like this.
> well it actually implemented a normalization pipeline and a tax computing engine which then did the taxes, but close enough You can't seriously believe laymen will try to implement their own tax calculators.
Are you one of those naive people that still take these coding benchmarks seriously?
If this happens to software development, this will happen to most mental jobs.
CRUD
Oh, like the LLM OS?
Sure. Reading a book is a much more difficult and ultimately, productive, task than writing a book.
Ok I will bite. Every single example you gave is in a hobby project territory. Relatively self-contained, maintainable by 3-4 devs max, within 1k-10k lines of code. I've been successfully using coding agents to create…
We squash, but still rebase. For us, this works quite well. As you said, rebasing needs to be done carefully... But the main history does look nice this way.
Yeah. It's pretty telling to look at profiles of people who replied to his tweet.
Well put. The standard practice is to hire a scientist and a developer, both with deep expertise, and have them work together. For a successful collaboration, it's obviously desirable for them to have some…
Personally, hard disagree. There were improvements, yes, but the last year felt particularly stagnant to me
Did you claim the same a year or two ago? Why or why not?