Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

The Eternal Sloptember

geohot.github.io

Post reply on HN
Print view View original

311–320 of 389 posts

Re: The Eternal Sloptember

#311

Post by bmenrigh »

Every C program I've had codex write ended up costing me more time than had I just done it from the start myself. Whereas almost every Python program it's written for me saved me time, even including the time I spent cleaning it up.

I chalk this up to primary two reasons. First, I cared a lot more about the implementation details of the C program than I did the Python one, and second, it's just better at simple stand-alone python programs than it is at C programs.

The criteria I know use is "do I care about the implementation details of this?". If I do (because for example it's going to be long-term code that I need to maintain) then the agent likely isn't worth it. But if I don't, there are huge efficiency gains to be had using the agent.

Re: The Eternal Sloptember

#312

Post by tonyedgecombe »

sodafountan wrote: post #156
tonyedgecombe wrote: post #139

Earlier quoted context omitted.

Bad news! The horse population declined by 85% after the widespread introduction of the car.

Good News! I learned something today.

I wouldn’t get too excited, I got that figure from ChatGPT. Who knows if it’s correct.

Re: The Eternal Sloptember

#313

Post by hansmayer »

pickleRick243 wrote: post #300
hansmayer wrote: post #230

Earlier quoted context omitted.

> But it seems everyone is arguing about whether LLMs can be perfect software engineers That's just those of us with longer memory holding the AI companies to the standards they declared themselves. Nobody forced Sam Altman to blab about a team of pocket PhDs, did they? I don't want the crap that does it correct 60℅ of the time - where is the god damn nation of PhDs in a datacemter already? Where is the AI doing all…

You want the AI that's doing all the SWE work in 3-6 months? Somehow I doubt that.

No buddy, not me. Dario Amodei however, keeps announcing it every about 6 months, on the dot. Last time i January this year. So I just want them held acccountable to their own statements. Otherwise if they would be untrue, that is at best incompetence, and at worst investor fraud. Both should draw serious consequences, given the ungodly sums which are burnt into these pipe dreams.

Re: The Eternal Sloptember

#314

Post by swiftcoder »

seanmcdirmid wrote: post #177
swiftcoder wrote: post #161

Earlier quoted context omitted.

> There is too much money involved for any rational debate. For the Sam Altmans of this world, sure, but how much money is the average AI booster commenting on HN actually standing to make?

If you are just invested in an index fund, a lot. If you are an HN commenter who is more likely invested heavily in tech stocks, much more than a lot. The other side is the stability of your job or job prospects, and we are adversely affected by that instead.

> If you are an HN commenter who is more likely invested heavily in tech stocks, much more than a lot.

The current state of the stock market is not exactly inspiring confidence about stability over the next few years. Number goes up over sufficient timescales, but if we get a Dotcom-level bust when AI investment slows, there may be a ways to climb back to current levels...

Re: The Eternal Sloptember

#315

Post by linsomniac »

>But each time I suspected I could have done it better and faster manually.

I've heard this said so many times, but my experience has just been so dramatically the opposite that it rings false. But geohot seems to be a pretty productive and smart guy, so it's hard to just dismiss what he's saying.

I get the sense that he's truly one of the 10x engineers. And maybe he can do it faster and better manually. But for those of us who aren't 10x, I think it lets us bridge that gap. Now we're getting back to "status anxiety": is this an attack on his ego, if the average becomes 10x?

Anecdote: Over 2 weeks of spare time, I used AI tooling to build a fairly sophisticated debian package caching proxy server (~72KLOC, 27K implementation, 45K tests). This would have easily taken me 6 months of focused time to implement by hand. I literally couldn't have done it because I can't take that much time off work and I have other weekend/evening obligations.

Re: The Eternal Sloptember

#316

Post by jreynar »

Another problem with perception of AI tools, for coding and other things, is that people often adopt a one-size-fits-all view. If Claude/Codex whatever can fix a bug in my tiny hobby project then it's going to revolutionize all software engineering. If it can write a haiku, then it the great American novel will be dead in a few years and the novelists will starve.

There aren't many truly general purpose tools so viewing things this way seems like either a fantasy or an over-reaction. And if nothing else the processes we use will have to change along with the tools.

It's the early days so we still have a lot to figure out but one of the most significant is which tools are appropriate for what sort of tasks. I've had good luck refactoring a small code base, building some small hobby projects and building features for our company's product. But, I've also dodged bullets doing greenfield development on some features where Claude (my default) has made what seemed like sound choices early on, and which I approved of, only to build something fragile or with unforseen consequences. I haven't quite figured out what distinguished those situations from the successful ones but I'm trying. But it's complicated by the fact that things are evolving quickly and yesterday's failure mode isn't the same as today's and, for that matter, yesterday's successes aren't guaranted to be repeatable today.

Re: The Eternal Sloptember

#317

Post by tavavex »

t-3 wrote: post #246
bruce511 wrote: post #197

Earlier quoted context omitted.

Goods are usually (although not always) inferior when made by a machine. A hand-crafted solid wood table is still superior to something from Ikea. Of course hand made tables are expensive. They service a sliver of the market. Ikea serves the rest of us who'd prefer not to eat off the floor. Fundamentally, Luddites didn't like being replaced by a machine. They were skilled workers, who used to have very desirable skil…

> Goods are usually (although not always) inferior when made by a machine. A hand-crafted solid wood table is still superior to something from Ikea. False. Ikea is not representative of machine-made products, just their own brand of cheap and poorly-designed machine-made products which outsource assembly to the customer for novelty value. Machines are much more precise than humans and do tedious and complex work with…

I know it's not the point of the conversation, but this is very overly harsh to Ikea. Their products are cheap (or, at least, they focus on cheap products), but why poorly-designed? I never had any of their furniture fail on me, and the concessions they make to get the lower price are really not deal-breakers in 99% of cases. It's really not bad at all. Also, selling disassembled furniture saves them a fortune on shipping, they don't do it because they think it's funny or quirky or something.

Re: The Eternal Sloptember

#320

Post by syl5x »

linsomniac wrote: post #315

>But each time I suspected I could have done it better and faster manually. I've heard this said so many times, but my experience has just been so dramatically the opposite that it rings false. But geohot seems to be a pretty productive and smart guy, so it's hard to just dismiss what he's saying. I get the sense that he's truly one of the 10x engineers. And maybe he can do it faster and better manually. But for thos…

Exactly my thoughts, I believe that the 10x engineers are basically living in a bubble and completely oblivious to the average developer/engineer (I consider myself average). Yes the LLMs cannot bring the level of sophistication that geohot would have but they totally could satisfy the needs of an average developer and their average job. More than 95% engineers are not having the problems that geohot is solving and most of our works is straightforward that any LLM can do, thus enabling us to do more of the same and possibly focus on slightly abstract problems if we have the time. Someone said couple of months ago that manual coding will be a privilege and I see that now.
Post reply on HN