dvfjsdhgfv

I'm very worried one day Apple will start enforcing upgrades to Tahoe just like Microsoft is doing with Windows.

I'm doing a lot, I see a lot of improvement, I see a lot of uses, but still consider the current generation of agentic coding simply not working for something more than a toy project - no matter how much skills, harnesses and what not you include. Happy to be proven otherwise, but Anhtropic's CCC is a good case in point.

So?

> Since I discovered pi I cancelled my Claude subscription and subscribed to ChatGPT.

Sorry, what is pi and how are you using it with ChatGPT for agentic coding?

Literally everyone is desperately trying to figure out why it's so bad and how to make it work consistently using harness etc. But in spite of this massive effort things always go awry after a while. Maybe in a year or two someone figures it out.

Frankly, I created dozen of such projects in the last weeks. Recently I just deleted them all. I feel like there's no point. I cancelled my Claude subscription, too.

I got back learning from books and use LLMs for "review my code in depth and show me its weak points" occasionally.

> - a side project to do rough cuts of family travel videos (https://usefirstcut.com, soft launch video: https://x.com/xitijpatel/status/2026025051573686429)

I can't comment about the quality of the code you delivered for your client so I checked your side project. Unfortunately it looks like there is only a landing page (very nice!) but the way from a vibe-coded project to production is usually quite long.

> A smarter model would be great but there are bigger productivity gains to be had with a good set up, a faster model, and abstracting away the need to think about agents or context usage. I’m still figuring out a good set up. Something with the speed of Haiku with the reasoning of Opus without the overhead of having to think about the management of agents or context would be sweet.

I was thinking about this recently. This kind of setup is a Holy Grail everyone is searching for. Make the damn tool produce the right output more of the time. And yet, despite testing the methods provided by the people who claim they get excellent results, I still come to the point where the it gets off rails. Nevertheless, since practically everybody works on resolving this particular issue, and huge amounts of money have been poured into getting it right, I hope in the next year or so we will finally have something we can reliably use.

> If you aren't doing this level of work by now, you will be automated soon.

It's harder and harder to detect sarcasm these days but in case you're being serious, I've tested a similar setup and I noticed Claude produces perfectly plausible code that has very subtle bugs that get harder and harder to notice. In the end, the initial speedup was gone and I decided to rewrite everything by hand. I'm working on a product where we need to understand the code base very well.

Man this is maddening.

For those confused about this submission: the original post is here:

https://web.archive.org/web/20260314105751/https://backnotpr...

Claude will happily generate tons of useless code and you will be charged appropriately. the output of LLMs has nothing to do with payment rates, otherwise you end up with absurdities like valuating useless CCC that was very expensive to build using LOCs as a metrics whereas in reality is a toy product nobody in their right mind would ever use.

Can you share a setup that works for you? I found vanilla opencode vastly inferior to CC, I use it only for little toys like 3 small files that's all.

I tried to pin my comment. It turned out after we migrated to the cloud version, this option disappeared and the ticket is flooded with commit messages making it essentially useless for humans. Rovo obviously faked a solution:

https://community.atlassian.com/forums/Jira-questions/How-to...

Actually once I was very surprised when testing one of recent non-thinking Qwen models it said "I'm sorry, this project is too complex, I can do that". I was very impressed by this answer. So far, it was the only model that reacted to this task, ever. The remaining ones agreed to proceed and failed.

nice

I kind of get it, they push it down my throat on every minor upgrade, "Do you want Apple intelligence?" - but there is no button "Why would I?".

I upvoted it because of the whole context, i.e. Microsoft ban and lock: https://www.windowslatest.com/2026/03/02/microsoft-gets-tire...

> Nope, Apple is sitting out the AI race.

That's why I use an iPhone. I don't need and I don't want any "AI" in my phone. The claims that people want it comes from CEOs, marketers and influencers of GenAI companies, not from users.

It's not only about security (although that's extremely important) but also making the changes necessary to adapt to the changing ecosystem. Unmaintained means there is nobody responsible, nobody you can even contact to make the changes needed. If there is anyone, even an aging OS developer as in the case of many packages, it's so much better than none.

The counterargument by the other side will always be, if we don't do it it doesn't matter because the Chinese will do it anyway - and then, common people will be at a disadvantage.

> Will vibe coding end like the maker movement?

No, because too much money has been pumped into it.

As it's hosted on CSAIL, I was somewhat disappointed by the code quality section:

https://missing.csail.mit.edu/2026/code-quality/

Although it's specifically code quality, not software quality, I feel so much is missing. Of course there is no space to explain it in detail, but they could at least list/mention things like complexity, maintainability, modularity etc.

Twitter requires login to view the replies, might use an alternative:

https://nitter.net/Persona_IDV/status/2025048195773198385

> I personally see consumer and entertainment spending, and people employed lucratively in these sectors, growing dramatically.

You may be right. OTOH, one could say the last decade had the best conditions ever to create the best movies, and yet for some reason I feel that the newer the movie is, the less soul it has.

What you say is missing crucial details, it simply doesn't add up. Near-zero for what? What was it for? Was it the classic "I deployed too many services and forgot to set up budgets" or was there something else?

I wouldn't say it sucks, I'd say it's very far away from what people with vested interest claim it to be.

No, and it's difficult for me to understand why anyone would ever want that.

> IMHO it wasn't that common to replace batteries, anyway.

Well, it was the most common thing to do for me - after a couple of years, you notice the battery performs worse, so you order a new one and enjoy brand new performance. Now it's hard to do even for laptops, especially some brands.

Since some job offers require a linked in link, I maintain an empty page explaining why maintaining a LI account is a privacy and security hole. It turns out it works.