I still have friends who work there. Some of them came to Apple from Be or Eazel, and are still working on Finder, Safari, Dock, etc. A lot has changed and in my opinion not for the best. Compared to them, my time there was a flash in the pan. When I look at Safari, Finder and the general state of the UI, I am deeply saddened. I see a bizarre combination of stagnancy, gratuitious change and general aimlessness across the desktop and mobile. I also have a deep distrust of anyone who works at big company, let alone a big company on one component for a long amount of time. To me, it leads to a focus away from external customers and to becoming an expert at internal politics. I probably need counseling, but I loved the dictatorship of the Steve era. Yes, we can point to flaws like the Mac Cube or the hockey puck mouse, but I really appreciated someone just maniacally fixated on getting things done and cutting through the BS that I saw later on in jobs in big tech.
It would be nice if veterans of the post-Steve era would post on here. Maybe they are scared, bound by NDAs or could care less. Like I said, I need some mental health treatment about my time(s) at Apple I was there working on Final Cut Pro after Be, went to Eazel, and then rejoined Apple as part of Steve's mass hiring of Eazel employees at the behest of Andy Hertzfeld.
Sounds like you are using ChatGPT to spit out a script in the chat? - if so, you should give 5.2 codex or Claude Code with Opus 4.5 a try... it's night and day.
I don’t think so. My favorite tool is Codex with the 5.2-codex model. I use Github Copilot and Codex at work and Codex and Cursor at home. Codex is better for harder and bigger tasks. I’ll use Copilot or Cursor for small easy things. I think Codex is better than Claude Code as well.
Are you using the same models and thinking levels for each?
I too have found Codex better than Copilot, even for simple tasks. But I don't have the same models available since my work limits the models in copilot to the stupid ones.
I have GH Copilot from work and a personal Claude Code max subscription and have noticed a difference in quality if I feed the same input prompts/requirements/spec/rules.md to Claude Code cli and GH Copilot, both using Opus 4.5, where Claude Code CLI gives better results.
Maybe there's more going on at inference time with Claude Code cli?
It is likely because GH Copilot aggressively (over-)manages context and token spend. Probably to hit their desired margins on their plans. But it actively cripples the tool for more complex work IMO. I've had many times where context was obviously being aggressively compacted and also where it will straight truncate data it reads once it reaches some limit.
I do think it is not as bad as it was 4-6 months ago. Still not as good as CC for agentic workflows.
I find this really frustrating and confusing about all of the coding models. These models are all ostensibly similar in their underpinnings and their basic methods of operation, right?
So, why does it feel all so fragile and like a gacha game?
In this case they probably are prompting it "wrong" or at least less well than codex/copilot/claude code/etc. That's not a criticism of the user, it's an indication of the fact that people have put a lot of work into the special case of using these particular tools and making sure they are prompted well with context etc whereas when you just type something into chat you would need to replicate that effort yourself in your own prompt.
A counter argument - the Switch gave game devs a solid platform to target without being the latest and greatest without compromising the usability or fun factor
I've heard that argument before, but I don't buy it. Whole PC gaming is a counter argument. Let developers make games that scale according to hardware, instead of excusing things with weak specs.
Even in PC gaming, the performance target tends to be the lowest performing current gen console, not the best PC.
Which is a totally reasonable approach and has given my PC years of usefulness even though better equipment is out there.
The cutting edge of PCs is such a tiny minority of users, even amongst PC gamers it's still a fraction of users.
That was not always the case for PC gaming, on modest means in my teens I could at least keep up with graphics card releases. I don't bother with that now, because I don't have to and gain very little from doing so.
> Even in PC gaming, the performance target tends to be the lowest performing current gen console, not the best PC.
I would have said "even static websites don't care about older hardware". I am very happy that Valve doesn't refresh the SteamDeck every year exactly for that reason: developers can target "the SteamDeck" instead of "the latest 3 SteamDecks" and force me to buy one every 3 years.
Sales numbers are also why Steam isn't in a particular rush to release another. It's popular to adult nerds. Outside of that, it's pretty poor selling when compared to essentially all consoles. The Dreamcast outsold it and Sega gave up on hardware cause of that thing. The PS Vita outsold it and it caused Sony to give up on handhelds. Meanwhile, the Switch 2 has pretty much no compelling reason to purchase it yet (an alright Donkey Kong game?) and outsold the Steam Deck's multi-year sales in a month.
reply