Hacker Newsnew | past | comments | ask | show | jobs | submit | csto12's commentslogin

As someone who doesn’t code in C and does more analytics work (SQL), is the code generated here “production grade?” One of the major criticisms I hear about llms is they tend to generate code that you wouldn’t want to maintain, is that the case here?

It's not bad. Skimming the code I'd say it's not enterprise quality but it's definitely better than an amateur throwaway project.

Those statements are mostly out of date and symptomatic of pre-agent-optimized LLMs. Opus 4.5 with clarifying rules in the CLAUDE.md does a good job at following idiomatic best practices in my experience.

That said, I'm mixed on agentic performance for data science work but it does a good job if you clearly give it the information it needs to solve the problem (e.g. for SQL, table schema and example data)


Not my experience. All frontier models I constantly test, agentic or not, produce code less maintainable than my (very good) peers and myself (on a decent day).

Plus they continue to introduce performance blunders.

Crying wolves, on day maybe there will be a wolf and I may be the last of us to check whether that's true.


Is OpenAI really a “tech startup” at this point?

It is until it IPOs or is profitable.

I believe there is a rule where the HN title should mirror the article’s title

Why Spain?


Who knows. But thats the country up the most last year.


Ah yes, the good old investment advice: if a stock has been going up, it’s time to buy.

Good luck with that strategy.


I heard this about NVDA in 2020 and 2021 and 2022 and 2023 and 2024 and 2025 and now 2026… if the stock is going up it is 100% time to buy if you know what the F you are doing. if you don’t know what you are doing then you sell when the stock is going up :)


If you know what you are doing, you do not rely on external random and irrational signals like market price.

Also, past performance is not an indicator of future performance. Hindsight is always 20/20.


> you do not rely on external random and irrational signals like market price.

I don’t, but too many people do :)


Oh and what’s your strategy Mr. Buffet?


For one, Mr Buffet coined the aphorism “be fearful when others are greedy, and greedy when others are fearful” and here you are suggesting the literal opposite.


I don’t think one year of outperformance counts as greed. There’s a reason I didn’t recommend gold.


Nice. Now take the car sales out of the vacuum and let’s see how great sales look year over across the world. Now let’s factor in how Elon’s government ended subsidies for electric cars. Should I go on?


You think they have “advanced AGI” and are worried about keeping up with the software industry? There would be be nothing to keep up with at that point.

To use an analogy, it would be like spending all your time before a battle making sure your knife is sharp when your opponent has a tank.


Do you have a source on this? That’s really interesting if true.


Sure. There are many studies but here is one.

Will Dobbie & Roland Fryer (NBER)

This study uses regression-discontinuity around exam cutoffs at Brooklyn Tech, Bronx Science, and Stuyvesant. It finds increased rigor of coursework but little impact on SAT scores, college enrollment, or college graduation, which are key predictors of lifetime earnings (and typically closely linked to earnings outcomes).

https://www.nber.org/system/files/working_papers/w17286/w172...


The schools studied in that paper are free, or close to free. Not $50,000 per anum And I don't think OP was suggesting it's the quality of education that affects outcomes in attendees of expensive private high schools.


There are very similar studies for private schools, can't find this second


You joke but a16z is already in talks to invest in this exciting AI opportunity


Can they please prompt their way to not having Claude go down every 4 days? Thank you.


I think you now know why it does


When is this from? I would be shocked if in 2025 most Spark was being written in Scala



I think the info is even more outdated than that. The article is from August 2024 but it cites "a recent survey by Databricks" that from what I can tell isn't linked to, so who knows what data they're referring to.

I was deep into the big data ecosystem in the 2010s. Those numbers feel like they're from 2017 or so. Scala has been on a slide every since.


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

Search: