Hi! Romain here, I work on Codex at OpenAI. We totally hear you. The team actually built the app in Electron specifically so we can support Windows and Linux as well. We shipped macOS first, but Windows is coming very soon. Appreciate you calling this out. Stay tuned!
Electron? Why can't Codex write, or at least translate, your application to native code instead of using a multi-hundred-mb browser wrapper to display text? Is this the future of software engineering Codex is promising me?
Only thing i'd add re windows is it's taking us some time to get really solid sandboxing working on Windows, where there are fewer OS-level primitives for it. There's some more at https://developers.openai.com/codex/windows and we'd love help with testing and feedback to make it robust.
When you're a trillion dollar company that burns more coal than Bangladesh in order to harness a hyperintelligent Machine God to serve your whims, you don't have the resources to maintain native clients for three separate targets.
Going cross platform doesn’t sound the main reason (or I hope not). For a company that size, is it really hard to hire specialised small team?! It would be a good show case for their Codex too
It is hard because this product will likely be obsolete next year based on how quickly AI is changing and evolving. Speed is king when you're on the frontier
If you were going to release a product for developers as soon as it was ready for developers to try, such that you could only launch on one platform and then follow up later with the rest, macOS is the obvious choice. There's nothing contemptuous about that.
Kudos to the OpenAI reps for responding to my comment and doing so politely.
My ire was provoked by this following on from the Windows ChatGPT app that was just a container for the webpage compared to the earlier bells and whistles Mac app. Perceptions are built on those sorts of decisions.
I (like I'm sure many others) predicted it in 2007 and hedged against it by getting a 10 year fixed mortgage at then-current rates on the basis that rates would go sky high as they had in earlier recessions in the UK.
They plummeted to next-to-zero, and in addition to the injury I had to endure the insult of the people who hadn't seen it coming gloating about their low standard variable rates.
Ofc I clearly didn't have much real economic understanding but I guess I am saying that beyond normal common financial sense (the lack of which at scale leads to these situations) which you should be using anyway, we don't really know which way the wind is blowing, and what the exact consequences will be.
Prepayment penalties are illegal for the vast majority of loans that consumers can get in the US, which makes it a no-brainer to refinance any time the payment saving exceeds the cost of writing a new loan.
The Trump admin has floated the idea of allowing prepayment penalties in home mortgages, BTW.
Crap, I was wrong. Bill Ackman is trying to convince Bessent to do it. So while it may happen, it isn’t coming from inside the admin.
One argument is that it could allow for lower rates, BTW. (This is true, it very well could).
And also, if it happened it would be for newly issued mortgages. Existing mortgages have language in the contract that you couldn’t just unilaterally change
The same way callable bonds command a higher interest rate than non-callable do. If the bond holder can just decide that tomorrow it’s cheaper for them to pay off the bond vs pay me the coupon on it, it’s worth less to me as a buyer. I lose if interest rates go lower (bond is paid early) or higher (I am now holding a bond worth less than a newly issued one).
If you look through the bond market you will sometimes see bonds issued by the same company or agency both as callable and non-callable, the callable bonds are usually .5-1% lower even when issued on the same date.
Your lender definitely wants to get paid back, but they don’t necessarily want to get paid back right now. Because then they have a pile of money and they need to find something to do with it.
Consumers have a tendency to pay loans back early when the bank doesn’t have any more profitable alternatives. Consumers also have a tendency to NOT pay loans back early when the bank does have more profitable alternatives.
But you know that the first situation is worse for the bank than the second situation. So they do account for this, to a degree, when they give you a loan. In theory they would be willing to give you a lower interest rate if you gave up your prepayment option. In theory. In reality? Who knows.
Sounds right but another big factor is to get some predictability.
Demand for mortgage varies over time, regulations change. It's a long term product, banks like to know with high certainty that when someone signs up it will be X earned over a period, not maybe X minus we don't know over an unknown period.
They are in the business of capital efficiency. Lack of control makes capital less efficient, or at least more expensive to keep efficient.
Overpayments (in the UK) are often not allowed, when they are, the borrower needs to arrange it when the loan is taken, and for a fee.
Refinancing is a right, but the fine prints told borrowers at what penalty.
I remember the opposite, just before we left the ERM (European Exchange Rate Mechanism). Interest rates hit 15% and one of my colleagues was gloating about how he had just taken on a fixed rate mortgage. A few days later we left and interest rates plummeted.
I feel like you and dang should at least use different phrases to fool the stylometry if you want us to believe that you are different people rather than a convoluted plot to provide dang an alibi :)
And the Agent saw the response, and it was good. And the Agent separated the helpful from the hallucination.
Well, at least it (whatever it is - I'm not gonna argue on that topic) recognizes the need to separate the "helpful" information from the "hallucination". Maybe I'm already a bit mad, but this actually looks useful. It reminds me of Isaac Asimov's "I, Robot" third story - "Reason". I'll just cite the part I remembered looking at this (copypasted from the actual book):
He turned to Powell. “What are we going to do now?”
Powell felt tired, but uplifted. “Nothing. He’s just shown he can run the station perfectly. I’ve never seen an electron storm handled so well.”
“But nothing’s solved. You heard what he said of the Master. We can’t—”
“Look, Mike, he follows the instructions of the Master by means of dials, instruments, and graphs. That’s all we ever followed. As a matter of fact, it accounts for his refusal to obey us. Obedience is the Second Law. No harm to humans is the first. How can he keep humans from harm, whether he
knows it or not? Why, by keeping the energy beam stable. He knows he can keep it more stable than we can, since he insists he’s the superior being, so he must keep us out of the control room. It’s inevitable if you consider the
Laws of Robotics.”
“Sure, but that’s not the point. We can’t let him continue this nitwit stuff about the Master.”
“Why not?”
“Because whoever heard of such a damned thing? How are we going to trust him with the station, if he doesn’t believe in Earth?”
Excellent summary of the implications of LLM agents.
Personally I'd like it if we could all skip to the _end_ of Asimov's universe and bubble along together, but it seems like we're in for the whole ride these days.
> "It's just fancy autocomplete! You just set it up to look like a chat session and it's hallucinating a user to talk to"
> "Can we make the hallucination use excel?"
> "Yes, but --"
> "Then what's the difference between it and any of our other workers?"
transient conciousness. scifi authors should be terrified - not because they'll be replaced, but because what they were writing about is becoming true.
reply