HN user

solumunus

966 karma
Posts2
Comments1,083
View on HN

My app is written in TypeScript. With agents I could rewrite it in Rust, I just don’t need to so I don’t. It doesn’t warrant that level of performance and the business logic is more digestible in its current form. Given the amount of reviewing I need to do now, readability is worth more than performance. There are always tradeoffs.

Are you implying that them attempting a Rust rewrite would fail, and this is why they’re not doing it?

No, I don’t think so, and searching seems to confirm my view. Inconvenience of switching is just one aspect.

There’s little difference between Coke and Pepsi and the barrier to switching is nil, yet clearly the products have stickiness. People have slight preferences and become familiar with the brand and then engagement becomes habitual.

The effects on margins are irrelevant to this.

I think they stickiness is less about the difficulty of switching and more about the lack of desire. I’ve been using Claude since day one, it works well and I’m happy, I like it. I’m sure Codex is good too. Switching from one to the other certainly isn’t going to be a game changer, the discourse shows me the differences are marginal.

Probably the only reasons I would seek change are economical.

The valuations are unjustified even at the prices they’re charging now.

They’re going to try their best to offload these investments into our pensions before the inevitable crash.

For luxury brand bags that cost $2-10k you pay around $300-600 for high quality counterfeits, but they really are almost identical. Sometimes they are higher quality.

Codex Resets 4 days ago

Such a counting method doesn’t explain that incredible growth. Do you think day by day huge portions of users are using additional devices in perpetuity?

Surely the ability to drive or work wood is separate to the knowledge required to gain the ability? An LLM can explain how to drive, how a car works, wood working processes… Some knowledge is difficult to communicate through text, and consumption of text might be a poor way to gain the ability to use it, but the knowledge is there?

Thanks for the models guys, sorry for your losses. Once this reality becomes mainstream and undeniable, surely the bubble pops and then what then. Future model development stops? Becomes private? Becomes a public effort?

Ukraine were no where near joining NATO at the time, although as it turns out - if they were their motivation would have been entirely valid. Russia didn’t want Ukraine to join NATO because it would prevent them from annexing Ukraine, that’s simple logic.

within 48 hours they were engaged in negotiations with Ukraine that involved 0 land concessions

So you think the plan was to invade Ukraine to scare them into a hand shake that they wouldn’t join NATO? I really don’t want to insult you but…

It's nowhere near the same thing.

This was supposed to be an imperialist land grab by Russia. This war did not emerge organically. Russia had a goal, to seize Ukraine - easily and quickly. Russia have failed at that goal. Failing is not winning. Not only have they failed to secure their objective, the attempt to do so has cost several orders of magnitude more than intended. The land they do control is of low value.

Again, spectacularly failing to carry out your goals is not "winning", in any sense of the word.