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

Codex for almost everything

openai.com

Post reply on HN
Print view View original

451–460 of 600 posts

Re: Codex for almost everything

#451

Post by subscribed »

badrequest wrote: post #403
someotherperson wrote: post #224

Earlier quoted context omitted.

Competition is bad? Who cares - let the big players subsidize and compete between each other. That's what we want. We want strong models at a low price, and we'll hype up whoever is doing it. Simultaneously, we also hype up the open models that are catching up. That are significantly more discounted, that also put pressure on the big players and keep them in check. People aren't falling for PR; people are encouraging…

It's hilarious how much this post reads as drafted by an LLM. The emdash, "it's not X, it's Y" framing, incredible.

People use em-dashes all the time. This is why LLMs use it too. Also guess how LLMs learnt to use "it's not X, it's Y".

Re: Codex for almost everything

#452

Post by mrtksn »

ttanveer wrote: post #440
mrtksn wrote: post #26

Codex is my favorite UX for anything as it edits the files and I can use the proper tooling to adjust and test stuff, so in my experience it was already able to do everything. However lately the limits seem to have got extremely tight, I keep spending out the daily limits way too quickly. The weekly limits are also often spent out early so I switch to Claude or Gemini or something.

I imagine the generous limit we felt were just from the 2x codex was offerring. I also felt the regression, and only recently remembered they had this.

I'm aware of the 2x limits but IIRC that was supposed to be until 9th of April or something like that and I wasn't hitting the limits especially the weekly one. Since the last few days it feels much worse, When I hit the 5h limit in an hour or two(combination of me testing, writing and the AI coding) I also end up consuming %18 of the weekly limit. So I have like 11h a week of work window. Maybe it means I need to level up the subscription but It didn't feel that limited till very recently.

Re: Codex for almost everything

#453

Post by jampekka »

piokoch wrote: post #439
cjbarber wrote: post #14

My current expectation is that the Cowork/Codex set of "professional agents" for non-technical users will be one of the most important and fastest growing product categories of all time, so far. i.e. agents for knowledge workers who are not software engineers A few thoughts and questions: 1. I expect that this set of products will be extremely disruptive to many software businesses. It's like when a new VP joins a co…

Maybe. The point is that in case of software it is fairly easy to verify if that what LLM produced is correct or not. Compiler checks syntax, we can write tests, there is whole infrastructure for checking if something works as expected. In addition, LLM are just text generating algorithms and software is all about text, so if LLM see 1 000 000 a CRUD example in Python, it can generate it easily, as we have a lot of c…

LLMs nowadays make aggressive use of web search. Thus they don't answer only on the base of what they were trained on.

I don't think they are much more prone to using only the same popular frameworks, especially if you ask them to weigh for options.

Re: Codex for almost everything

#454

Post by jbstack »

TeMPOraL wrote: post #444
ryandrake wrote: post #101

Earlier quoted context omitted.

I agree, in general we are going to find that ultimately most employee end users don't want it. Assuming it actually makes you more productive. I mean, who the hell wants to be 10X more productive without a commensurate 10X compensation increase? You're just giving away that value to your employer. On the other hand, entrepreneurs and managers are going to want it for their employees (and force it on them) for the ab…

I want. If I get 10X more productive, I can unilaterally increase my compensation 10X by doing my stuff in 1 unit of time instead of 10 it took, and splitting the remaining 9 units of time into, say, 4 units of time doing more work, securing my position and setting myself up for promotion, and 5 units of time doing whatever the fuck I want . Not all compensation shows up in a bank account - working less, or under les…

You want it, but then you closed by explaining exactly why you shouldn't want it. Plus, the new baseline isn't neutral (as in, everyone is the same again). If humans can now do 10x the work as before, the employer doesn't need the same number of humans to carry out its work. So the new baseline is actually "let's keep 1 employee and fire the other 9", unless the business can find a way to suddenly expand 10x so that it needs 10x as much work done.

Re: Codex for almost everything

#457

Post by roel_v »

troupo wrote: post #54
cjbarber wrote: post #45

Earlier quoted context omitted.

> Non-technical users expect a CEO's secretary from TV/movies: you do a vague request, the secretary does everything for you. LLMs cannot give you that by their own nature. What are you using today? In my experience LLMs are already pretty good at this. > Please for the love of god actually go outside and talk to people outside of the tech bubble. In the past week I've taught a few non-technical friends, who are well…

> What are you using today? In my experience LLMs are already pretty good at this. LLMS are good at "find me a two week vacation two months from now"? Or at "do my taxes"? > how to use Cowork. Yes, and I taught my mom how to use Apple Books, and have to re-teach her every time Apple breaks the interface. Ask your non-tech friends what they do with and how they feel about Cowork in a few weeks. > I think where our vie…

"LLMS are good at "find me a two week vacation two months from now"?"

Of course they are. I gave one a similar prompt a few weeks ago, albeit quite a bit more verbose (actually I just dictated it, train of thought, with couple of 'eh actually, forget what I just said about x, do y instead") and although I wasn't brave enough to give it my credit card and finalize the bookings, it would have paid for the bookings I had it set up for me, had I done that. I gave it some RL constraints, like "we're meeting friends in place xyz at such and such date, make sure we're there then" and it did everything from watching we wouldn't be spending too many hours driving per day to check that hotels are kid friendly to things to do and see and what public holidays there are so that we know when supermarkets close early and a bunch of details I wouldn't have thought of. It checked my (and my wife's) calendar, checked what I had going on work wise, etc.

That is a fully solved 'problem' man. LLMs will run the whole thing for you. Just provide it with the login details to booking websites and you're off to the races.

I did have it upgrade the car, even if that pushed the cost outside the budget I gave it. Next time it'll know LOL.

Re: Codex for almost everything

#458

Post by King-Aaron »

yes_man wrote: post #423
ryandrake wrote: post #101

Earlier quoted context omitted.

I agree, in general we are going to find that ultimately most employee end users don't want it. Assuming it actually makes you more productive. I mean, who the hell wants to be 10X more productive without a commensurate 10X compensation increase? You're just giving away that value to your employer. On the other hand, entrepreneurs and managers are going to want it for their employees (and force it on them) for the ab…

If everyone becomes 10x more productive it won’t mean the companies cash flow 10x’s. Where value is loose there is competition, so in theory everyone should win. Unless nobody else can compete to capture that loose 10x value, in which case congratulations, you are now a unicorn. Of course in reality in the short term what happens is companies lay off people to increase margins. Times will be tough for workers, and eq…

Tasks have value because they take effort to complete.

If you remove the effort from those tasks, they will have no value.

10x the value of 0 is 0

Re: Codex for almost everything

#459

Post by weeb »

MassiveQuasar wrote: post #165
Avicebron wrote: post #159

Earlier quoted context omitted.

I've helped an otherwise very successful and capable guy (architect) set up a shortcut on his desktop to shut down his machine. Navigating to the power down option in the menu was too much of a technical hurdle. The gap in needs between the average HNer and the rest of the world is staggering

right clicking start menu and clicking shutdown is too hard? amazing

Ah yes, this task fails hard at the xkcd.com/627/ tactic of "Find a menu item or button that looks related to what you want to do..."

What do I want to do? "turn off my computer" What button do I press? "start"

Re: Codex for almost everything

#460

Post by magicalhippo »

jorl17 wrote: post #84
avaer wrote: post #29

Earlier quoted context omitted.

Hot take: we (not I, but I reluctantly) will keep calling it code long after there's no code to be seen. Like we did with phones that nobody phones with.

Very much agree. Everyday people can now do much more than they could, because they can build programs. 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. Today, when we think of someone "using the computer" we gravitate towards people using apps, installing them, writing d…

> Everyday people can now do much more than they could, because they can build programs.

Indeed. Just spoke to a buddy, he's got some electronics knowledge, he's been code-curious but never gotten past very simple bash scripts and Excel sheets (vlookup etc to drive calculations).

He got himself a Claude subscription and has now implemented a non-trivial Arduino project, involving multiple CAN-bus modules and an interactive, dynamic web interface to control all this. The web interface detects the CAN-bus modules and populates the web interface based on that, and allows him to adjust the control logic.

It's a project he's had in his head for a few years and now was able to realize on his own (modulo Claude).

Post reply on HN