Live data from Hacker News

The Eternal Sloptember

geohot.github.io

261–270 of 389 posts

Re: The Eternal Sloptember

#261

I wish these posts that talk about non-human mistakes that agents make would post some examples. They would be interesting to see.

One nasty set of bugs Claude recently introduced; it was doing a large refactor which involved changing call sites to conform to a changed API. Tedious, but straight forward. It helpfully added about 50 if(!something) continue; statements, this would make the code silently absorb issues that should have thrown. Had I accepted this, the results would have made the program run like shit but not crash, making debugging much harder than it needs to be. Really effing annoying! Thanks Claude!

Re: The Eternal Sloptember

#262

I don't think LeCun is saying they won't be able to program. I think he says we won't hit AGI. Programming does not require AGI; it's a pretty specific skill! -- I think this article is COPE, if I'm being quite honest. I thought of putting cute analogies, like the C programmers saying the Python and Javascript programmers are not "hardcore" enough... but the truth should be obvious to anyone using LLMs effectively. -…

> it's a force majeur

I assume you meant something like 'force multiplier"? Force Majeure is an uncontrollable event that prevents a party from fulfilling a contract. Which some may argue is what AI will also deliver. :)

Re: The Eternal Sloptember

#263
post #215

Earlier quoted context omitted.

> I'm in the "haven't written any code in a while" boat ATM How long do you think it will be before you can't write any code because you're out of practice? One of the dangers of engineering management is that it can turn you into a person that can no longer do the thing. Does that even matter?

The ability to read code doesn’t decay at nearly the same rate. Neither does your experience.

I read plenty of books, but I'd struggle to write one because that's a different skill that I don't have.

Re: The Eternal Sloptember

#264
On Saturday I thought I had vibe coded myself into a mess. I had implemented a new block type in my structured editor for Practal Zero (or rather let Codex do it), and suddenly the syntax highlighting broke in the whole document. Asking Codex to fix it didn't work. I was contemplating to restart the whole project on a basis that I actually fully understand, but that would set me back so much when the first reasonable prototype seemed so close. Instead, I took a walk.

See, the project actually has a well thought out structure that I design carefully, but more and more of it gets filled out by Codex. Codex is not smart enough to remember all the high-level design considerations, some of which had not been documented because I was just implicitly assuming them. So the fix was to use Codex to isolate the error, think about in terms of the high-level design, and fix the problem, which was partially an implementation problem, and partially a problem of the high-level design.

I fixed the high-level design with discussions with Codex, and documenting this, and then let Codex implement the fixes. The discussion took me more than an hour, the implementation was done in a few minutes.

This working style is similar to doing math: You have a high-level idea of what you are doing, and let that guide you, and Codex assumes the role of something that fills out all of the details you take for granted. Often it turns out your high-level idea had flaws, and this shows up in your code not working as expected. So you revise your high-level idea, refactor the code to reflect the modified high-level design, rinse and repeat.

Working this way is still really hard, but it allows me to do things I could not have done before. Getting your ideas validated (or refuted) in minutes instead of days is huge, and makes it possible to march through stuff that would have turned into a deadly swamp before, at least for me.

Now. Do I think that most corporate programmers will use Codex or CC in this way? I don't know, but I think probably not. So what will stop them going into the swamp until it swallows them, instead of backing up in time and marching around it?

Re: The Eternal Sloptember

#266

Earlier quoted context omitted.

条 is the appropriate measure word for pants; they're plural in English, but uncountable (like other nouns) in Chinese. You could translate it as "a pair of pants", and that's the appropriate way to put it in English, but really it says "one pants".

I guess the measure word works equivalently to a unit of measurement, then. One bottle of beer, one sack of sugar, one 条 of pant.

Correct. In Chinese all nouns require them.

(It's not the case, however, that all measure words require nouns. 天 ("day") and 年 ("year") are measure words that are almost always used on their own. There might be an implicit notion of "one day of time" or similar.)

Re: The Eternal Sloptember

#267

Earlier quoted context omitted.

I think you are misrepresenting the luddites. They were not against technological progress. Many of them were the ones who invented the machines. What they were fighting for were labour rights and distribution of power. They were fighting against enshitification by some guy who stole their collective inventions and by force kicked them out. They were not against more clothes for everyone - quite the opposite. They we…

The Luddites-as-labour-movement view is not entirely wrong, but also misses a lot. They were also an elite group that fought to preserve their own status and the exclusion of women from the industry. I thought this was a pretty good post about it: https://www.verysane.ai/p/against-the-luddites

I am no expert but from books I've read on the topic. It was also pretty diverse movement as is usual with decentralized movements like this. There absolutely were lower class people present who saw it as labour movement.

In other words. The Luddites as elite group that fought to preserve status view is not entirely wrong, but also misses a lot.

In context of audience here - programmers (elite group). You can say that programmers fighting with AI do it to preserve their own status. Or we might trust those (like geohot) who are angry because it's just leading to bad results. It's enshitification - of the result, the working conditions, the ethics. The whole chain.

Re: The Eternal Sloptember

#268
When I started coding with AI I would copy / paste code into GPT-3.5 and ask it to update the code, it was a massive productivity boost, minor changes, fully reviewed. Then VSCode allowed tabbing, it was okayish, but I had my finger on the pulse and knew exactly what was changed and had an opinion on the suggestions. Then cursor allowed you to see and approve changes, after a few changes it started making bigger changes but had an review and approve process, things were starting to feel more magic and required more discipline to be on top of changes. Then YOLO mode hit and you could make massive changes, slowly it became easier and easier to just let the AI build code and you just guide it.

The issue is people mix up complexity, novelty, repeatability and scale.

Well documented complex problems can easily be solved by LLMs.

Doing the same thing over and over again is easy for an LLM.

Novelty and scale is very hard for an LLM.

Even small novel problems confuse LLMs.

When you start a new code base the LLM smashes through the boilerplate work. Then when it gets to scale it struggles with context rot plus novelty.

Re: The Eternal Sloptember

#269
"When people see an artifact, they make assumptions about the process that was used to create it. Without even thinking about it, they assume the creator had a basically human state of mind. This assumption is no longer true."

I've been running into this experience with non-code artifacts, like slideshows and documents.

Re: The Eternal Sloptember

#270
post #160
post #74

I think a lot of the problem with the current discourse is how black-and-white it is. Either you're a luddite or "ai pilled". In most cases, LLMs can get you 80-95% of the way, sometimes less, sometimes more. And heck, sometimes, it just gets you somewhere wrong. But it seems everyone is arguing about whether LLMs can be perfect software engineers in isolation running in a closet, and using that to say that LLMs do n…

It's funny, but the more I know about the true Luddites, the more I see their point of view. " the original Luddites were primarily protesting against machinery used to "fraudulently and deceitfully" manufacture inferior goods, bypass labor standards, and strip skilled artisans of their livelihoods."

In the end, the worst part wasn't just loosing artisan jobs and destroying the market for crafted goods. The second order effect was to create a new kind of drudgery in the repetitive and sometimes dangerous work of maintaining the operations of the machine. It created a class of workers who were completely dependent on these kinds of jobs.
Post reply on HN