Live data from Hacker News

Codex for almost everything

openai.com

511–520 of 600 posts

Re: Codex for almost everything

#511
post #482

Earlier quoted context omitted.

> 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. If they have any surplus of money (or loans) they'll try, so those 9 employees may end up becoming team leads or middle management, trying to start new initiatives to get the 10x expansion (and 100x improvement). The market isn't anywhere nea…

lol that has nothing to do with market efficiency. I’ve seen a number of your posts where you talk about topics you clearly are not all that well versed in, with such confidence when you’re plain wrong.

Of course it does have to do with market efficiency, of which the inertia and surplus within companies (especially large ones) is a part.

> I’ve seen a number of your posts where you talk about topics you clearly are not all that well versed in, with such confidence when you’re plain wrong.

I'm sure it's true. However, since you brought it up, can you be more specific and name three?

Re: Codex for almost everything

#512
I enabled the computer use plugin yesterday. Today I asked it to summarize a slack thread, along with a spreadsheet without thinking about it

I was expecting it to use MCPs I have for them, but they happened to not be authenticated for some reason

I got _really_ freaked out when a glowing cursor popped up while I was doing something else and started looking at slack and then navigating on chrome to the sheet to get the data it needs

Like on one hand it's really cool that it just "did the thing" but I was also freaked out during the experience

Re: Codex for almost everything

#514
post #259

Earlier quoted context omitted.

Probably accessibility APIs

Which specific ones though allow you to send input to a window without raising it? People have been trying to do "focus follows mouse [without auto raise]" for a long time on mac, and the synthetic event equivalent to command+click is the only discovered method I'm aware of, e.g. used in https://github.com/sbmpost/AutoRaise There is also this old blog post by Yegge [1] which mentions `AXUIElementPostKeyboardEvent` bu…

You don't actually need to send CGEvents to UI elements to make them do things ;)

Re: Codex for almost everything

#515

Earlier quoted context omitted.

Which specific ones though allow you to send input to a window without raising it? People have been trying to do "focus follows mouse [without auto raise]" for a long time on mac, and the synthetic event equivalent to command+click is the only discovered method I'm aware of, e.g. used in https://github.com/sbmpost/AutoRaise There is also this old blog post by Yegge [1] which mentions `AXUIElementPostKeyboardEvent` bu…

Maybe they used Claude to come up with a good method to do this. /s But I was also wondering, how this even works. The AI agent can have its own cursors and none of its actions interrupt my own workflow at all? Maybe I need to try this. Also, this sounds like it would be very expensive since from my understanding each app frame needs to be analysed as an image first, which is pretty token intensive.

There are better ways to analyze on-screen content than images.

Re: Codex for almost everything

#516
post #500

Earlier quoted context omitted.

(I work at OpenAI) Heya, in reality it's more much organic than that. We build stuff, ship it internally, then work crazy hard to quickly ship it externally. When we put something out on a given day, it's usually been in the works and scheduled for a while. One concrete example: to set up a launch like today, where press, influencers, etc, all came out at 10a PT. That's all coordinated well in advance!

We cannot trust identity like we used to here on HN (even pre-LLM-AI I thought we seemed naive.) Unfortunately, we live in a world or anyone or any AI can claim almost anything plausible sounding. Where do we go from here? (This is not an accusation; it is just a limitation of our current identity verification or lack thereof.)

You can confirm that the people who say things are in a position to know.

Re: Codex for almost everything

#517

Maybe I lack imagination, but I just can't figure out what I'd use this for. I'm finding AI helpful in writing code (especially verbose Unreal Engine C++ code) as a companion to my designs, but, I really don't want it using my computer. I dunno, I guess the other use case would be summarizing slack or discord but otherwise this seems to me like a solution in search of a problem.

Going on an old legacy website, downloading reports, summarizing them, and then doing things based on those

Or basically any app without MCP capabilities

I ask the AI daily to summarize information across surfaces, and it's painful when I have to go screenshot things myself in a bunch of places because those apps were not made to extract information out of them, and are complete black boxes with a UI on top

Re: Codex for almost everything

#519

There seems a fair enthusiasm in the UI of these to hide code from coders. Like the prompt interaction is the true source and the actual code is some sort of annoying intermediate runtime inconvenience to cover up. I get that productivity can be improved with a lot of this for non developers, just not sure using 'code' as the term is the right one or not.

I think the intent is more "we won't need coders" ... the real goal is to get to the point where Product Managers can just write specs and a working product comes out the other end.

These people HATE that developers have been necessary and highly paid and, in their view, prima donnas. I think most of the people running these companies actually despise developers.

Re: Codex for almost everything

#520
post #463

Earlier quoted context omitted.

> There seems a fair enthusiasm in the UI of these to hide code from coders. Like the prompt interaction is the true source and the actual code is some sort of annoying intermediate runtime inconvenience to cover up. I've finally started getting into AI with a coding harness but I've take the opposite approach. usually I have the structure of my code in my mind already and talk to the prompt like I'm pairing with it.…

This is the way. The funny thing is my expectation was that adoption of AI coding would kill the joy of getting into a flow state but I've actually found myself starting to slip into an alternate type of flow state. Instead of hammering out code manually over an hour the new flow state is a back and forth with the LLM on something that's clear in my mind. It's a collaborative state where I'm ultimately not writing mu…

Yeah - similar thing for me as well. A lot of times there would be something I want to work on that would be boilerplate/repetitive/laborious work and I would just procrastinate it for as long as possible, working on other things, until I'd finally get around to doing it. Now those are just immediately completed with a simple prompt and instead of going with the initial implementation, I have the bandwidth to tweak and refine details that I would have skipped over before just to ship.
Post reply on HN