autoconfig

This line of reasoning will shut down practically any interesting conversation that has to do with wanting to change the system. Extremely unproductive.

The charitable interpretation here is obviously that the LoCs are equivalent in quality, in which case it is a very useful metric in the context that was presented. The inability to infer that should be embarrassing.

My initial experience with Opus 4.7 has been pretty bad and I'm sticking to Codex. But these results are meaningless without comparing outcome. Wether the extra token burn is bad or not depends on whether it improves some quality / task completion metric. Am I missing something?

> When creation was hard, skill was the differentiator: you had to actually be good to make something worth showing. Now the barrier is near zero, so you need reach. Reach costs money or it costs years. Probably both.

Creation has progressively been getting easier since the invention of the computer, it is not a new phenomena. This naturally pushes the boundary on what needs to be delivered in order to find paying customers. In other words, creation still is "hard" if you want to succeed.

> I launched something last week. 14 people signed up — no ads, just a couple of posts. 14 real people who didn't have to. That number is tiny and it felt like something. Then I sat down to think about what it would take to grow it and I couldn't look at that math for very long.

This applies to 90+% of founders that have ever launched something. The hard part comes from continuing to push forward when you experience this (which you will over and over). It sounds like the author expects that what was hard suddenly should be easy.

"It never gets easier, you just go faster" - Greg LeMond

> This requires calling native APIs (e.g., Win32), which is not feasible from Electron.

That is not correct. One of the major selling points of Electron is precisely that you can call native APIs.

This thesis has existed since Cursor first started, and the gap between them and VSCode has only widened since then. It’s worth spending some time thinking about why that may be before having such strong conviction about their demise.

It’s beyond shameful that chrome on android doesn’t support shared workers yet. We decided to simply nix multi tab support on android because of it.

Either you care about being correct or you don't. If you don't care then it doesn't matter whether you made it up or the AI did. If you care then you'll fact check before publishing. I don't see why this changes.

I think the incorrect premise here was that engineers always know what a good product is. :) And I say that as an engineer myself. It's fully possible that the whole team was aligned on a product idea that was bad, it happens all the time. From my experience though, if there's any company where engineers don't just mindlessly follow the PMs and have a lot of agency to set direction, it's Meta. Might differ between orgs but generally that was my experience.

That is not at all how things work at Meta. The impact of the things you deliver as an engineer has a direct effect on your performance review. For better or for worse, that also means that engineers have a ton of leverage on deciding what to work on. It's highly unlikely that the engineers working on this were laughing at it while doing so.

Don't assume that you can simply pattern match because you've been at another big company. I've been at three, meta being one of them. And they have all operated very differently.

Aider operates on your file tree / repo and edits and creates files in place. So it at least lessens the copy / paste drastically. This is a very different experience than using chatgpt or Claude on web. Still not ideal UX compared to having it in the IDE though to be clear.

Where did I say that it's AGI? I was addressing the parent's comment:

> "Reminds me of autonomous vehicles a couple of years back".

I don't think any reasonable interpretation of "autonomous vehicle" includes the ability to change a tyre. My point is that sometimes hype becomes reality. It might just take a little longer than expected.