You can ask it to make the changes in appropriate PRs. SOTA model + harness can do it. I find it useful to separate refactors and implementations, just like with humans, but I admittedly rely heavily on multi-provider review.
I've always said if corporations were governments they would be totalitarian fascistic dictatorships. This is just them evolving to their final form. No idea why anyone would want to work at a corporation like Meta by choice the same way I don't understand why anyone would move to North Korea, but I guess the money is just that good.
This is a big reason why retail product barcode stickers (not barcodes printed directly on a package as it comes from the manufacturer) are now commonly printed on frangible stock with built in slices in it which breaks apart in 3, 4 or more pieces if you try to peel it off.
Price tags have been constructed like this since the 1970s. The little gummy paper ones with literal prices stamped onto them. They fragment into about six pieces if you pick at them and try to pull them off an item.
I noticed this straightaway and my mother informed me how bad people would try and swap price tags on items and this was a countermeasure.
Later on, when I owned my own vehicle, it was the common lore that, after applying a new annual registration tag to the license plate, we should go over it with a razor blade, and slice up about six sections on the little sticker, because there were criminals out there who would lift off the registration sticker because it was quite valuable to fraudulently "register" license plates that way and bypass the DMV. Although I never saw this crime actually perpetrated or met anyone who was a victim, I guess I did it myself a few times. Better safe than sorry!
Saying "corporations have lied in the past for their own self interest" and then pointing to two very well known examples does not imply or over generalize that all corporations do that.
The point isn't to demonize all corporations, it's to say specifically that a pathology of some megacorporations is broadscale lying to the public about the safety of their products for personal gain.
Labeling power evil is not automatic, its just making an observation of the common case. Money-backed power almost never works for the forces of good, and the people who claim they're gonna be good almost always end up being evil when they're rich and powerful enough. See also: Google.
Google is the company that created a class-less non-hierarchical internet. Everyone can get the same access to the same services regardless of wealth or personhood. Google is probably the most progressive company to ever exist, because money stops no one from being able to leverage google's products. Born in the bush of the Congo or high rise of Manhatten, you are granted the same google account with the same services. The cost of entry is just to be a human, one of the most sacrosanct pillars of progressive ideology.
Yet here they are, often considered on of the most evil companies on Earth. That's the interesting quirk.
> Google is the company that created a class-less non-hierarchical internet.
Can you explain what you mean by this? I disagree but I don't understand how you think Google did this so I am very curious.
For my part, I started using the internet before Google, and I strongly hold the opinion that Google's greatest contribution to the internet was utterly destroying its peer to peer, free, open exchange model by being the largest proponent of centralizing and corporatizing the web.
The alternative was a teleco AOL style internet with pay tiers for access to select websites. The free web of the 90's would remain, but would be about as culturally relevant as Linux.
Surely you have to recognize the inconsistency of saying that Google "corporatized" the web, while the vast majority of people using google have never paid them anything. In fact many don't even load their ads or trackers, and still main a gmail account.
If we put on balance good things and evil things google has done, with honest intention, I struggle very hard to counter "gave the third world a full suite of computer programs and access to endless video knowledge for free with nothing more than dumpy hardware", while the evil is "conspired with credit card companies to find out what you are buying".
This might come off like I am just glazing google. But the point I am trying to illuminate is that when there is big money at play, people knee-jerk associate it with evil, and throw all nuance out the window.
Besides, IRC still exists for you and anyone else to use. Totally google free.
No I actually do understand where your opinion comes from now and I partially agree. I had forgotten about how badly the ISPs wanted the internet to mirror Cable TV plans.
There’s several subjects to go into here and HN probably isn’t the best place for the amount of detail this discussion requires but I will just note the amount of people blocking Google’s ads and trackers is negligible and has significantly shrunk in the mobile first era.
The wave is shifting to other corporations now but for a good while most of the internet was architected to give Google money. Remember SEO? An entire practice of web publishing centered around Google’s profit share. That hasn’t disappeared- it’s just evolved and transformed into more ingrained rent-seeking.
Yes, the code is still important. For example, I had tasked Codex to implement function calling in a programming language, and it decided the way to do this was to spin up a brand new sub interpreter on each function call, load a standard library into it, execute the code, destroy the interpreter, and then continue -- despite an already partial and much more efficient solution was already there but in comments. The AI solution "worked", passed all the tests the AI wrote for it, but it was still very very wrong. I had to look at the code to understand it did this. To get it right, you have to either I guess indicate how to implement it, which requires a degree of expertise beyond prompting.
Yep, all models today still need prompting that requires some expertise. Same with context management, it also needs both domain expertise as well as knowing generally how these models work.
Do you ask it for a design first? Depending on complexity I ask for a short design doc or a function signature + approach before any code, and only greenlight once it looks sane.
I understand the "just prompt better" perspective, but this is the kind of thing my undergraduate students wouldn't do, why is the PhD expert-level coder that's supposed to replace all developers doing it? Having to explicitly tell it not to do certain boneheaded things, leave me wondering: what else is it going to do that's boneheaded which I haven't explicit about?
Because it's not "PhD-expert level" at all, lol. Even the biggest models (Mythos, GPT-Pro, Gemini DeepThink) are nowhere near the level of effort that would be expected in a PhD dissertation, even in their absolute best domains. Telling it to work out a plan first is exactly how you would supervise an eager but not-too-smart junior coder. That's what AI is like, even at its very best.
That's not the best framing, IMO. More important is, even a PhD expert human wouldn't one-shot complex programs out of short, vague requests. There's a process to this. Even a thesis isn't written in one, long, amphetamine-fueled evening. It's a process whose every steps involves thinking, referencing sources, talking with oneself and other people, exploring possibilities, going two steps forward and one step back, and making decisions at every point.
Those decisions are, by large, what humans still need to do. If the problem is complex, and you desperately avoid needing to decide, then what AI produces will surprise you, but in a bad way.
I understand that but 1) expert-level performance is how they are being sold; but moreover 2) the level of hand-holding is kind of ridiculous. I'll give another example, Codex decided to write two identical functions linearize_token_output and token_output_linearize. Prompting it not to do things like that feels like plugging holes in a dyke. And through prompting, can you even guarantee it won't write duplicate code?
I'll give a third example: I gave Codex some tests and told it to implement the code that would make the tests pass. Codex wrote the tests into the testing file, but then marked them as "shouldn't test", and confirmed all tests pass. Going back I told it something to the effect "you didn't implement the code that would make the tests work, implement it". But after several rounds of this, seemingly no amount of prompting would cause it to actually write code -- instead each time it came back that it had fixed everything and all tests pass, despite only modifying the tests file.
In each example, I keep coming back to the perspective that the code is not abstracted, it's an important artifact and it needs/deserves inspection.
Note to self: don't go away for the weekend without HN ;-)
Personally I run several agents. At minimum Codex and Claude, so they cross-check each other. Exactly to avoid what you describe. Duplicate functions or "tests all pass" when nothing was implemented is the kind of thing a second model, reading the diff with fresh eyes, tends to flag immediately.
But it takes coordination and solid skills + rules to make it work. Tomorrow's battle -> AI skillers.
> the code is not abstracted, it's an important artifact and it needs inspection.
That's a rather trivial consideration though. The real cost of code is not really writing it out to begin with, it's overwhelmingly the long-term maintenance. You should strive to use AI as a tool to make your code as easy as possible to understand and maintain, not to just write mountains of terrible slop-quality code.
The diff: +8000 -4000
reply